AIニュース 2026-06-10

Business World Model

Businesses are increasingly adopting AI-enabled tools to improve productivity, reduce costs, and enhance products and services. However, the transformative potential of AI extends beyond automating predefined tasks: it lies in enabling intelligent systems to plan, optimize, and execute business initiatives from high-level strategic objectives. This paper introduces the concept and architecture of a business world model (BWM), a world model specialized for business and organizational environments. Inspired by world models in artificial intelligence, cognitive science, and control theory, a BWM encodes business states, dynamics, constraints, objectives, and feasible action space to support autonomous decision-making. We propose a business-semantics-centric formulation in which business states, dynamics and actions are linked to key business entities. Within this framework, agents can simulate alternative action sequences, estimate their effects on future business outcomes, and evaluate trade-offs under uncertainty. The proposed architecture integrates semantic data representations, probabilistic machine learning models, deterministic business rules, and explicit action space into a coherent structure for planning and counterfactual reasoning. Although its individual components are not new, the contribution of BWM lies in organizing them as an executable internal simulator for business initiatives. This work establishes a conceptual foundation for autonomous business systems capable of moving from instruction-based execution toward goal-driven planning and execution.

Deployment-Time Memorization in Foundation-Model Agents

Foundation-model agents are increasingly long-lived systems that remember users across interactions, making memorization an explicit deployment-time function rather than solely a property of model weights. Existing work addresses parametric memorization or audits fixed memory configurations, but does not characterize how memory-design choices jointly shape personalization utility, extraction risk, and deletion fidelity. We study this surface as deployment-time memorization, formulating agent memory as a privacy-utility frontier measured by Personalization Recall (PR) and Adversarial Extraction Rate (AER), and sweeping three memory-design knobs: summarization aggressiveness, retrieval breadth (k), and deletion mode. We further introduce the Forgetting Residue Score (FRS) to quantify whether deleted information remains recoverable from derived memory tiers. On LongMemEval, key-fact summarization reduces canary extraction by 76% on Gemma 3 12B and 64% on GPT-4o-mini while preserving nearly all personalization recall; critically, once content is compressed away, increasing k no longer restores leakage. The same compression, however, induces a deletion-fidelity failure: raw-only deletion leaves derived summary copies recoverable in approximately 20% of instances, and only full-pipeline purge or tombstone redaction drives worst-tier residue to zero. Together, these results establish that persistent agent memory must be evaluated as a first-class memorization mechanism -- assessed by what it helps agents recall, what it makes extractable, and what it can truly erase.

Exploratory Responsiveness and Adaptive Rigidity under AI-Assisted Optimization

This paper develops a theory of exploratory adaptation under AI-assisted optimization. The central argument is that the long-run adaptive effects of AI systems depend critically on how predictive assistance interacts with exploratory responsiveness itself. We formalize this mechanism using a dynamical framework in which cognitive, institutional, and technological systems evolve over rugged epistemic landscapes characterized by multiple locally reinforced configurations. A central state variable in the model is adaptive responsiveness, which measures the capacity of a system to traverse unfamiliar conceptual and institutional trajectories under changing conditions. Under convergent predictive regimes, AI systems substitute for exploratory engagement, reducing adaptive responsiveness and generating metastable trapping, hysteresis, premature convergence, and exploration-collapse dynamics in which systems become locally efficient but globally rigid. The framework also identifies contrasting exploration-enhancing regimes in which AI systems amplify exploratory search, conceptual traversal, and adaptive mobility. The effective substitution parameter is therefore responsiveness-dependent: systems possessing weak exploratory routines are more vulnerable to exploratory substitution, whereas systems already possessing high adaptive responsiveness may use AI assistance to expand exploratory mobility across rugged landscapes. The long-run adaptive effects of AI consequently depend not only on AI capability itself, but also on institutional structure, developmental context, and the architecture of human-machine interaction.

Predictive Assistance and the Temporal Dynamics of Exploratory Compression

Classical theories of cognition describe problem solving as exploratory search through structured problem spaces in which repeated interaction gradually compresses search into efficient representational structures. Predictive artificial intelligence systems introduce a distinct regime in which stabilization may occur before exploratory diversification unfolds, supplying solutions and decision trajectories prior to internally generated search. This paper develops a geometric dynamical framework in which attention evolves over a landscape of strategies shaped by stabilizing drift, endogenous exploratory perturbation, and responsiveness-gated learning. Predictive assistance is modeled as a process of exogenous exploratory compression that stabilizes trajectories before self-generated exploration broadens the accessible regions of strategy space. The framework yields three main results. First, sustained predictive stabilization reduces exploratory responsiveness by attenuating the effective influence of intrinsic perturbations even when exploratory variability remains present. Second, curvature accumulates and relaxes asymmetrically, producing hysteresis and delayed recovery of exploratory mobility after assistance withdrawal. Third, developmental outcomes depend critically on the timing of stabilization, with early intervention narrowing future exploratory traversal before broad representational diversification has occurred. The framework generates empirically testable predictions concerning exploratory entropy, premature convergence, and delayed recovery following predictive stabilization. More broadly, the results suggest that predictive systems may reshape the geometry of exploratory cognition itself.

From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs

Multimodal Large Language Models (MLLMs) can listen and see, but how do audio and visual signals actually travel through the network to shape an answer? Despite their growing role in research and real-world applications, the internal pathways through which audio and visual tokens influence the final prediction remain poorly understood. In this study, we examine audio-visual information flow inside Audio-Visual Large Language Models (AVLLMs), tracing how AVLLMs route, utilize, and integrate audio and visual information across two input configurations, audio-visual video and multiple interleaved audio-visual items. We find that for audio-visual video, AVLLMs follow the sequential information flow pathway established for VLMs and VideoLLMs, with audio and visual contribution flowing along this pathway in proportion to the task's reliance on each modality. In settings with multiple interleaved audio-visual items, this routing shifts to different parallel streams. Furthermore, we demonstrate that audio-visual and other token types can be discarded once their information is transferred to LLM, with minimal impact on the model's prediction or even slight improvement, generalizing across multiple tasks and datasets, enabling more efficient inference. These findings hold across multiple models and scales, Qwen2.5-Omni and Video-SALMONN2 Plus at 3B and 7B scales, leading to hypotheses on why these flow structures emerge. Together, these results deliver the first coherent picture of how AVLLMs orchestrate sound and sight inside the network and lay the groundwork for the next wave of interpretability, design, and efficiency advances in audio-visual and broader MLLMs.

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can cause context overflow, stale-state errors, and high inference cost. We study this problem in automated expense itemization in Microsoft Dynamics 365 Finance and Operations using Model Context Protocol tools. We evaluate four GPT-5 configurations on a 50-task hotel expense benchmark: no user model, full conversation history, context pruned to the last 5 tool call/response pairs, and pruning with automated summarization. Results are averaged across 5 independent runs, with the user model held constant for the context-engineering comparison. The no-user-model baseline achieves only 8.0% complete itemization. Full-context retention improves completion to 71.0%, but consumes 1,480,996 tokens and 14.56 hours per benchmark. Pruning to the last 5 tool calls improves completion to 79.0% while reducing token use to 535,274 and runtime to 5.39 hours. Adding summarization achieves the best result: 91.6% complete itemization and 99.64% average amount itemized, with 553,374 tokens and 5.79 hours. We further report confidence intervals, effect-size analysis, sensitivity over pruning and summary windows, failure analysis, results across five expense types grouped into three categories, and cross-model evidence with Claude Sonnet 4.5. These results show that, for this class of enterprise tool-use workflow, selective retention of recent tool interactions plus compact summarization can improve both reliability and efficiency compared with full-history retention.

Minimalist Genetic Programming

Genetic programming (GP) is based on two important insights. First, that any learning task can fundamentally be posed as a program induction problem, where the goal is to construct a symbolic hierarchical model that is expressed as a syntax tree. Second, to pose this task as a search problem, and use evolution to locate the desired model. Since it was proposed, GP has produced notable results in a wide range of tasks and problem domains. This work presents an alternative view by modifying the second core insight of GP, posing the problem as a syntactic derivation task instead. In particular, this paper presents Minimalist Genetic Programming (MGP), an algorithm that like GP is biologically inspired, but instead of evolution it takes inspiration from the Minimalist Program to human language, in which syntax is understood as an optimal solution to the problem of linking two other mental systems. In minimalism, the core computational process is a binary set formation operator called $MERGE$, than can be used to incrementally construct complex syntactic structures using a simple Markovian process. MGP is able to discover the core building blocks of the symbolic expressions, and to incrementally combined them using $MERGE$. The proposed system is benchmarked on symbolic regression tasks that are known to be difficult to solve with standard GP systems because of the propensity for bloat. Results show that when a proper lexicon of atomic syntactic objects are chosen, MGP is able to consistently produce the exact ground truth model on a set of symbolic regression where standard GP struggles to do the same. The insights provided by minimalism are shown to be relevant to the problem of program induction, and should be explored further based on the potential exhibited by MGP in this work.

Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraph

Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history. We show that an event-sourced agent runtime removes that friction and turns controlled improvement into a first-class workflow. When the agent's state is a deterministic projection of an append-only event log, failures are recorded, a run replays exactly from its log, candidate patches scope to typed pipeline seams, gates are auditable, and every promotion or discard is itself an event. We demonstrate this with Regimes, a loop on the ActiveGraph runtime that diagnoses failed evaluations, proposes a repair at a pipeline point, and promotes it only after static checks, sandbox execution, in-sample evaluation, and held-out validation. The loop is target-agnostic: the same control flow runs against different tasks through a common interface. On LongMemEval-S the dominant failure is not retrieval but reconciliation: the evidence is already in the assembled context, yet the reader answers incorrectly. Across five seeded held-out splits, Regimes discovers reader-prompt repairs that improve final held-out accuracy by +0.05 to +0.10 in four splits and +0.01 in one over-promotion split; two splits are individually significant (seed 5 unadjusted for its sequential promotion structure), and the pooled count is descriptive only, since the splits share one 500-question pool. The durable contributions are ActiveGraph as an auditable substrate that makes controlled improvement loops tractable, the held-out-gated loop it supports, the failure-regime taxonomy routing each failure to a pipeline location (whose marginal value over an unrouted baseline is the primary open question), and the prompt-as-discovery-probe hypothesis.

RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning

While Large Language Models (LLMs) have achieved near-perfect performance in \emph{solving} high-school mathematics, their ability to \emph{evaluate} the diverse reasoning processes of real human students remains under-examined. To bridge this gap, we introduce \textbf{RealMath-Eval}, a rigorously annotated benchmark of 224 real-world exam responses from high schools. Our initial evaluation reveals that even state-of-the-art LLM judges struggle significantly on this task, exhibiting a high Mean Squared Error ($\sim$2.96) against expert human grading. To probe a plausible explanation, we contrast this performance with a control setting where the same judges evaluate synthetic LLM-generated solutions. We identify a stark ``Evaluation Gap'': judges are considerably more accurate and consistent on synthetic text (MSE $\sim$1.17) but struggle to generalize to authentic student reasoning. Through semantic embedding analysis, we find that synthetic errors suffer from a ``structural collapse'' into predictable, low-dimensional linear subspaces, whereas human errors form a more diverse error space. Furthermore, generative probability probes suggest that human reasoning involves significantly higher information-theoretic surprisal, indicating that student reasoning transitions are more out-of-distribution for current models. Finally, we find that surface-level style transfer fails to close this gap. Our findings suggest that current LLM evaluation pipelines relying heavily on synthetic data may not adequately capture the diversity of authentic student mathematical reasoning.

Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching models not just what to predict but why. We test this assumption on five-year Alzheimer's disease and related dementias (ADRD) prediction from longitudinal health histories. Across a large-scale controlled experiment of 504 configurations, we find that rationale-based SFT consistently and substantially hurts prediction performance relative to label-only fine-tuning. The degradation persists across model families and data scales, and is not resolved by using a reasoning-oriented base model. Crucially, the failure is not explained by poor rationale quality: human expert annotation confirms that the generated rationales are medically accurate and faithfully grounded in patient-specific evidence, and few-shot experiments show that the same rationales improve performance when used as inference-time demonstrations rather than training targets. We identify the root cause as a structural conflict between narrative plausibility and discriminative optimization. We hope our work paves the path toward a more precise understanding of when and how rationale-based supervision helps and when it does not, guiding the responsible development of language models for high-stakes clinical prediction.

Sim2Schedule: A Simulator-Guided LLM Framework for Autonomous Open-Pit Mine Scheduling

Open-pit mine scheduling is a critical process for maximizing economic return under complex geotechnical and operational constraints. While Mixed-Integer Linear Programming (MILP) provides mathematically optimal baselines, its exponential computational complexity and inability to adapt in real time limit its practical deployment in dynamic industrial environments. This work introduces a simulator-driven Large Language Model (LLM) scheduling framework in which the LLM acts as an autonomous decision-making agent, guided at each step by a custom simulator that encodes geotechnical precedence, extraction-processing coupling, and dynamic capacity constraints directly into the action generation mechanism. Operating entirely zero-shot within a closed, data-secure environment, the framework produces complete, interpretable extraction and processing schedules without cloud-based inference, domain-specific fine-tuning, or retraining. To provide a trustworthy performance benchmark, a novel MILP formulation is developed that incorporates realistic operational and geotechnical constraints. Evaluated across mining instances of varying scale and time periods, the LLM-based framework recovers between 94\% and 99\% of the MILP optimal NPV while scaling linearly in computation time. These results position simulator-constrained LLM agents as a practical and scalable alternative to classical optimization for long-horizon industrial scheduling under complex operational constraints.

From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMs

When large language models generate from retrieved or augmented contexts, conflicts between external context and parametric priors remain a central reliability bottleneck. Existing contrastive decoding methods follow a \emph{context-aware} paradigm that unilaterally amplifies context over parametric priors, overwriting correct priors when the context is erroneous. We generalize this to the \textbf{conflict-aware} paradigm that dynamically allocates authority between prior and context based on conflict signals, rather than presupposing context trustworthiness. We show that the affine combination of prior and context logits yields a \textbf{power family} with an inherent \textbf{regime asymmetry}: extrapolation amplifies errors unboundedly when the prior is correct, interpolation under-corrects when the context is correct, and no static regime covers both. Existing contrastive decoding methods are instances of this family, mostly extrapolative. To evaluate both conflict directions, we propose TriState-Bench, a model-aware evaluation protocol that calibrates per-model prior knowledge to measure three conflict states: correction, resistance, and agreement. To resolve the asymmetry, we propose Adaptive Regime Routing (ARR), which routes between regimes at each step, lifting resistance EM from below 6 to 16--33 without sacrificing correction or agreement. Our code is available at https://github.com/keith-Jiang/conflict-aware-decoding.

What Spatial Memory Must Store: Occlusion as the Test for Language-Agent Memory

Language-agent "memory palace" systems anchor each memory to a world coordinate, on the intuition that geometry adds something text cannot. We make that intuition testable and report three results. First, the memory-palace default of folding spatial proximity into a linear blend beside recency and importance does not help and can hurt: in a pre-registered recall experiment the shipped blend fails its own frozen test (mean Delta-Hit@5 -0.0375, Wilcoxon p=0.306), sitting at a position-blind baseline, while a geometry-led weighting wins decisively (+0.3208, p0.000, pooled exact McNemar p=2.5x10^-29), a run that surfaced and fixed a real relay anchor defect. We concede that occlusion-needs-geometry is near-tautological; the contribution is the measurement and isolation, separating what spatial memory must store from how it is read. These pilots power a frozen confirmatory study (SPMEM-ZERO-REAL-PREREG-v1); the full human-authored multi-world study with blind raters remains future work.

Mobility Anomaly Generation using LLM-Driven Behavior with Kinematic Constraints

Although the study of human trajectory anomalies is critical for advancing spatial data mining, empirical research remains severely hindered by a pervasive lack of ground-truth datasets. Despite the availability of several real-world and simulated human trajectory collections, these datasets exclusively capture normal mobility patterns and lack annotated anomalies. This specific scarcity is fundamentally driven by the inherent statistical rarity of anomalous events, precluding the feasibility of conventional observational methods. Compounding this challenge, the systematic acquisition of large-scale mobility data is strictly bottlenecked by prohibitive costs and stringent privacy regulations. To overcome these fundamental limitations and establish a reliable human trajectory anomalies dataset with annotated ground truth, we introduce a novel, end-to-end generative framework designed to synthesize realistic trajectory anomalies at scale. Our architecture bridges the gap between purely synthetic mobility data and complex real-world physical constraints by operating directly on baseline simulated trajectories. We employ Large Language Model (LLM) agents to systematically inject semantically meaningful behavioral anomalies such as irregular out-of-distribution check-ins and skipped routine visits. To ensure rigorous spatial validity, the system leverages map-constrained routing reconstruction to recalculate the physical transitions between these LLM agent-modified staypoints. Moreover, to narrow the simulation-to-reality gap, we augment the resulting trajectories with a context-aware spatial noise model, parameterized by environmental and location-specific variables, to accurately emulate heterogeneous GPS sensor degradation.

Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts

Code-generating large language models (LLMs) increasingly produce visual artifacts such as charts, web pages, and slides by writing programs that are executed by non-differentiable renderers, committing to code before observing the render. As a result, otherwise executable code often yields artifacts with visually salient defects, including overlapping elements, clipped text, broken alignment, low contrast, and overflow. We study visual-feedback self-distillation for code-generated visual artifacts. We propose Visual-SDPO, a self-distillation policy-optimization framework that treats rendered visual feedback as privileged context for a weight-sharing teacher and distills this feedback into a coding student. To make supervision spatially targeted rather than uniform, we introduce Visual-Grounded Code Credit Weighting, which traces each detected defect back to the code statements responsible for the affected elements and amplifies the distillation signal on those statements. A sequence-level GRPO (Group Relative Policy Optimization) term complements the dense token-level objective by rewarding executable, visually high-quality rollouts, while failed executions remain learnable through the self-distillation path by passing execution errors as privileged context to the teacher. We instantiate Visual-SDPO for chart, web/UI, and slide generation with a unified Qwen3-VL-8B-Instruct backbone. Across chart-to-code, UI-to-code, and slide-generation benchmarks (ChartMimic, Design2Code, and AeSlides), Visual-SDPO improves over the zero-shot base by more than 10 absolute points in the primary metric and over GRPO by at least 2.4 points, with fewer training steps and no added inference-time cost.

Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning

Reinforcement learning has become a key paradigm for eliciting reasoning abilities in large language models, where exploration is crucial for discovering effective solution trajectories. Existing exploration methods typically encourage diversity in semantic or gradient spaces, without distinguishing what drives this diversity. A trajectory may appear novel because it follows a new reasoning process, or because it varies memorized patterns and shortcuts. Rewarding both cases equally may steer exploration toward memorization rather than genuine reasoning improvement. In this paper, we propose DiRL, a Direction-Aware Reinforcement Learning framework that anchors exploration to an internal reasoning-memorization direction of the policy. Specifically, DiRL extracts this direction from model representations, constructs direction-weighted gradient features to characterize rollout updates, and shapes rewards to amplify reasoning-aligned exploration while suppressing memorization-aligned variations. DiRL integrates seamlessly into standard Group Relative Policy Optimization (GRPO). Extensive experiments on mathematical and general reasoning benchmarks demonstrate the effectiveness of DiRL, showing significant improvements over various existing exploration methods.

ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience

AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforcement learning (RL) optimizes flows but is semantically blind to unstructured constraints. We introduce REFLECTICHAIN, bridging this gap through a Generative Supply Chain World Model (SC-WM) - encoding heterogeneous supply networks into a 6-dim graph-latent space with physical conservation - and Double-Loop Learning that separates epistemic uncertainty (KL-trust-region-bounded policy adaptation) from aleatoric uncertainty (stochastic latent rollouts). On Semi-Sim, a 10-node semiconductor benchmark with SIR risk propagation, 6 perturbation types, and 10 policy constraint templates, REFLECTICHAIN improves Rationale Consistency Score by 33.0% (p < 0.0001, d = 2.78), maintains 82.3% operability under adversarial shocks, and exhibits anti-fragile behavior (+40.2% gain under moderate pressure). We identify three operational epistemic mechanisms - uncertainty separation, knowledge-boundary detection, and empirical Bayesian policy updating - and discuss five limitation categories.

Belief-Space Control for Personalized Cancer Treatment via Active Inference

Cancer treatment is at the core a sequential decision-making problem with partial observability, latent patient heterogeneity, and explicit constraints on the budget for medical measurements. Unlike standard Reinforcement Learning (RL) approaches that control state trajectories, cancer treatments permanently modify patients' transition dynamics, changing how states evolve over time. We model cancer treatment as a belief-space planning problem using active inference, deriving an expected free-energy objective that unifies goal-directed control and information acquisition under measurement budgets without. We implement this framework using real clinical cancer data from the AACR Project GENIE Biopharma Collaborative dataset. Results on clinical data demonstrate a simultaneous patient categorization and high treatment efficacy, under real measurement and treatment constraints.

Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games

Recent advances in LLM-driven code evolution have enabled automated discovery by iteratively generating and improving programs. However, applying these methods to adversarial multi-agent games introduces a fundamental challenge: the evaluation landscape shifts as strategies improve, causing fixed evaluators to become unreliable and evolution to stagnate. We propose three mechanisms to address this challenge: evaluator co-evolution, which incorporates discovered champions into the opponent pool; hierarchical deep evaluation, which replaces noisy few-game scores with statistically reliable assessments; and weakness pressure, which dynamically up-weights the most difficult opponents to break through plateaus. We implement these mechanisms within FAMOU, a framework built upon the same foundation-model code-evolution paradigm as OpenEvolve and ShinkaEvolve. On the MCTF 2026 3v3 maritime capture-the-flag task, FAMOU consistently outperforms both baselines under two backbone LLMs, achieving the highest combined score (0.526) and the best generalization to unseen opponents (61.7% win rate), while ablations confirm that each mechanism contributes to performance. Notably, the LLM mutation process generates tactical structures entirely absent from the seed strategies -- including lookahead search and adaptive interception -- demonstrating that code-level evolution can produce nontrivial algorithmic innovations in adversarial settings. The FAMOU-evolved strategy further achieved 1st place in the hardware round-robin and 3rd in simulation at the AAMAS 2026 MCTF Competition, validating its real-world transferability. The optimized implementation and corresponding evaluation codes developed through our evolutionary process are available at: https://github.com/1xiangliu1/FAMOU-CoEvo

Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune

Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs. However, general-purpose large language models (LLMs) often misclassify financial entities or ignore domain-specific patterns. This paper investigates the use of DeepSeek-R1-8B, a recent open-source large language model, combined with Low-Rank Adaptation (LoRA) and Noisy Embedding Fine-Tuning (NEFTune) for financial NER. Each annotated sentence in our corpus of 1693 samples is converted into an instruction-input-output triple. We insert lightweight LoRA matrices into the Transformer layers and apply NEFTune to improve generalisation by adding uniform noise to embedding vectors during training. Experiments show that the LoRA-adapted DeepSeek-R1-8B achieves a micro-F1 of 0.901 on seven entity types (Company, Date, Location, Money, Person, Product and Quantity), and adding NEFTune further boosts the micro-F1 to 0.912, outperforming Llama3-8B, Qwen3-8B, Baichuan2-7B, T5 and BERT-Base baselines.

STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios

Large language models are increasingly used to power personal agents for everyday applications, but evaluating these agents remains a challenge. Existing benchmarks still rely on sandboxed artifacts, static task design, and coarse scoring, which hinder scalability and limit progress toward reliable personal-agent evaluation. This paper introduces STAGE-Claw, an automated framework for building and evaluating realistic personal-agent scenarios in state-based personal-computing environments. Given a task hint, STAGE-Claw automatically creates and validates a realistic benchmark task with its environment, task prompts, ground truth, and related verification programs. Agents are then evaluated in realistic operating environments, where performance is measured by the correctness of the final system state rather than only the textual response. Using STAGE-Claw, this paper creates a benchmark with 40 challenging real scenario agent tasks, evaluates 11 frontier models, and analyzes their task scores, costs, tool-call reliability, and common failure patterns. Overall, STAGE-Claw offers a scalable, state-based way to evaluate agents in realistic user scenarios.

A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis

The rapid evolution of financial technology demands sophisticated artificial intelligence systems capable of handling diverse challenges across multiple domains simultaneously. This paper presents a groundbreaking unified framework that seamlessly integrates Proximal Policy Optimization for robo-advisory systems, advanced time-series prediction models for high-frequency trading, in-context learning mechanisms for dynamic investment advisory, game-theoretic approaches for competitive banking scenarios, and unified embeddings for cross-modal financial sentiment analysis. Our comprehensive framework addresses the critical gap in existing literature where these technologies have been developed in isolation, failing to leverage their synergistic potential. Through extensive experimentation across multiple financial datasets and real-world scenarios, we demonstrate that our integrated approach achieves superior performance compared to specialized single-domain systems. Specifically, our framework shows a 23.7% improvement in portfolio optimization metrics, reduces prediction error in high-frequency trading by 31.2%, enhances investment recommendation accuracy by 18.9%, optimizes competitive banking strategies with a 27.4% increase in Nash equilibrium convergence speed, and improves sentiment analysis accuracy by 15.6% through cross-modal fusion. The theoretical foundation of our work establishes convergence guarantees for the integrated optimization problem, while our empirical results validate the practical applicability across diverse financial institutions. This research not only advances the state-of-the-art in financial AI but also provides a blueprint for developing comprehensive intelligent systems that can adapt to the complex, interconnected nature of modern financial markets.

Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness

Breakthroughs in large language models and multimodal generation technologies have propelled the digital reconstruction of human mental traits, emotional patterns, and long-term memory from science fiction toward engineering practice. Yet current research and industry practices at the intersection of AI and digital humans remain hampered by fundamental conceptual ambiguities: the essential differences between next-generation intelligent agents and traditional virtual humans, the construction pathways for digital entities possessing self-identity, and the core technical and ethical challenges confronting this domain all demand urgent clarification. This paper systematically examines the transformative logic underlying the transition from traditional virtual humans to the ``Soul Computing'' paradigm, driven by frontier AI technologies. We first analyze the evolutionary patterns of human consciousness and memory mechanisms, reassessing the core value of massive multimodal digital fragments in the reverse reconstruction of individual mental worlds. On this basis, we formally delineate the academic connotations of narrow and broad Soul Computing for the first time, clarifying its academic boundaries and essential distinctions from Affective Computing, Historical Reconstruction, and Mortal Computation. We argue that Soul Computing systems must architecturally construct an ``Intensional'' core rather than serving as purely ``Extensional'' functional carriers, thereby enabling the fundamental transition of AI from toolhood to living agency.

Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents

Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved through iterative error analysis. We present \textbf{Trace2Policy}, whose core mechanism -- \textbf{EISR} (\textbf{E}rror-driven \textbf{I}terative \textbf{S}kill \textbf{R}efinement) -- maintains a human-readable rule document as its optimization target: each round executes the rules on a validation set, clusters errors by root cause into MISSING, WRONG, or CONFLICT types, applies targeted patches, and commits only those that pass a regression gate. \textbf{For this class of compliance-sensitive, skewed-base-rate decision tasks, we identify rule quality -- not model capability -- as the dominant performance lever}: across five LLMs, one-shot distillation plateaus near $\sim$70\% on the deployed pool, while eight EISR rounds lift the same rules to 79.6\% when compiled into deterministic Python -- zero LLM calls at inference. \textbf{Execution form compounds the gain: in production, the same EISR-refined content runs 9.8~pp higher as compiled Python than as an LLM prompt, a form-and-engineering bundle the 22-day deployment matured together.} Deployed for 22 days at a major logistics carrier (3,349 audit cases), the compiled pipeline outperforms the pure-LLM baseline it replaced (72.7\%); on these calibrated, skewed-base-rate workloads, re-enabling LLM fallback monotonically degrades accuracy. An LLM-driven variant, \textbf{Auto-EISR}, reproduces this refinement at \$5--\$10 per cycle versus $\sim$70 expert-hours, and transfers to four public benchmarks spanning legal reasoning (LegalBench) and process-mining decisions (BPIC 2012) without re-engineering.

ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics

Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structural insight. Recent evidence suggests that even today's strongest frontier models remain uneven on Olympiad combinatorics, revealing a gap in creative mathematical reasoning. We introduce ComBench, an Olympiad-level combinatorics benchmark for evaluating and diagnosing the combinatorial reasoning capabilities of large language models. ComBench contains 100 human-annotated competition-level problems organized around two complementary settings: analysis-centric problems, which primarily require rigorous mathematical arguments, and construction-centric problems, which require explicit constructions in addition to correctness justifications. The evaluation protocol combines rubric-guided proof grading with deterministic construction verification, exposing cases where proof quality and construction validity diverge. Experiments on frontier open- and closed-source models show that ComBench is far from saturated: the strongest model reaches 65.4% overall Avg. and 75.3% overall Best@4. We further find that Rigorous Proof Reasoning and Constructive Realization are distinct capabilities: Kimi-K2.6 trails GPT-5.5 on analysis-centric proof grading but surpasses it on construction-centric Best@4, while Existence and Construction problems remain consistently hardest across representative frontier models.

A complementary study on PlanGPT: Evaluation with defined Performance Metrics and comparison with a planner

Automated Planning is a subfield of Artificial Intelligence (AI) where the main objective is generating a sequence of actions, known as a plan, that helps us reach a goal state from an initial state. A planning problem is defined by a set of objects, an initial state and a desired goal state. The objective is to compute a plan that'll lead us from the inital state to the goal state. Programs that generate plans are called planners. In this paper, we did a complementary study to the state-of-the-art LLM called PlanGPT which was released last year. We redid some experiments to verify whether planning with LLMs is \textbf{pertinent} and \textbf{worthwhile}. We also check whether the results obtained in the official PlanGPT paper for plan coverage were correct, and we also performed a more comprehensive study on PlanGPT's performance: in our paper PlanGPT's performance was evaluated using two metrics: Plan Cost and Plan Generation Time. The results of planGPT were compared to those produced by a traditional planner for the same plans and same metrics. We discovered that PlanGPT is no better than a Greedy search strategy.

A Reliable Fault Diagnosis Method Based on Belief Rule Base Consider Robustness Analysis

In equipment operation, the implementation of fault diagnosis is essential to ensure the continuity and safety of production equipment, improve operational efficiency and reduce maintenance costs. Since sensor readings are widely used for fault diagnosis, their reliability directly affects the results of fault diagnosis. A new fault diagnosis method is proposed to address the two problems of robustness assessment and robustness optimization of fault diagnosis models. For this purpose, a reliable fault diagnosis method based on a belief rule base (BRB) considering robustness analysis is proposed. Firstly, the robustness analysis of the BRB model is carried out systematically. Secondly, three robustness constraint strategies are proposed to optimize the robustness of the BRB fault diagnosis model. Finally, the effectiveness of the proposed model is verified by taking the fault diagnosis of WD615 diesel engine and Case Western Reserve University bearings as an example, and the experiments show that the proposed model improves both accuracy and robustness.

Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm

Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e.g., images) can guide a (smaller) student model building on another type of data (e.g., text/audio). Existing CMKD methods often require paired multi-modal data with aligned semantics, but obtaining such paired data are often costly and impractical. To mitigate this limitation, we develop a new CMKD framework for the more challenging setting where paired data are unavailable. In particular, we establish a cross-modal distributional relationship between teacher and student models, which reveals two fundamental quantities governing effective distillation: feature alignment and label alignment. These quantities characterize semantic discrepancy between modalities at the levels of representation and prediction distributions, respectively. Motivated by this insight, we propose a principled framework, with theoretical guarantees, that enables effective cross-modal knowledge distillation by aligning distributions rather than individual samples. Extensive experiments across a wide range of multimodal benchmarks show that our framework is highly effective in both unpaired and paired data settings, improving significantly over prior work.

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks. Existing methods have made progress through fine-grained credit assignment to alleviate long-horizon sparse rewards and hierarchical reinforcement learning to decompose tasks and reduce long-term dependency. However, these methods still do not directly address long-context interference, in which continuously growing histories weaken the agent's ability to track the global task state and impair subsequent reasoning and decision-making. Inspired by the way humans handle complex tasks through subgoal decomposition and completed progress summarization, we propose Hierarchical Planning and Information Folding (HIPIF) for long-horizon LLM agent learning. HIPIF trains the agent end-to-end to organize long-horizon execution around explicit subgoals while folding completed subgoal histories to reduce long-context interference. Furthermore, to stabilize subgoal-based planning and execution, HIPIF combines hierarchical reflection and subgoal-oriented process rewards to guide subgoal generation, transition, and execution, without relying on costly auxiliary models or task-specific expert trajectories. Extensive experiments on three publicly available agentic benchmarks demonstrate the validity of our method.

ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning

Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks. Existing memory mechanisms are largely centralized, typically organizing retrieved information and interaction history within a single model context. This design imposes a fundamental trade-off: scaling reasoning trajectories risks context overload, whereas aggressive content pruning may result in irreversible information loss. Seeking a better trade-off, we draw inspiration from human cognitive systems, especially the functional complementarity between the prefrontal cortex (executive control) and the hippocampus (memory management), suggesting that such a trade-off need not be inherent, but may instead stem from centralized memory organization. To this end, we propose ActiveMem, a heterogeneous framework that decouples agent memory from the core reasoning process. Specifically, a high-level Planner utilizes distilled semantic gists to execute reasoning, while a lightweight, distributed memory system operates in parallel to actively accumulate and consolidate these gists throughout the task. Experiments on BrowseComp-Plus and GAIA show that ActiveMem achieves state-of-the-art accuracy with significantly reduced overhead, demonstrating the effectiveness of distributed active memory for long-horizon reasoning.

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence. However, existing memory paradigms represent each memory item in raw text and image forms, so retrieval-based systems must pass the retrieved text or images to the generation LLMs/VLMs, resulting in high token consumption and storage pressure, making it unaffordable for resource-constrained applications. We propose Latent Memory, a latent-space memory paradigm that replaces each raw text or image evidence item with a single high-dimensional latent token produced by a small compressor LLM/VLM. Rather than retrieving raw evidence for generation, Latent Memory operates in a unified latent representation space: the query is embedded into this space to retrieve relevant latent tokens, and the retrieved latent tokens are directly prompted to a pretrained LLM or VLM for answer generation. To make each latent token simultaneously informative for reconstruction, retrieval, and generation, we train the compressor with reconstruction, contrastive, and distillation objectives in a unified end-to-end manner. Latent Memory is evaluated on seven text-only QA benchmarks (e.g., HotpotQA) and multimodal QA benchmarks, where it achieves competitive QA performance compared to advanced RAG baselines while consuming 3x to 10x fewer generator tokens. It can also deliver the strongest image-grounded QA performance on WebQA. Code is available at https://github.com/zz1358m/Latent-Memory-Master.

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts that exceed their finite context windows, making memory retention a fundamental resource-allocation problem. Existing memory systems improve management through heuristic scoring, retrieval optimization, or learned compression, but largely treat retention as a local decision problem and do not explicitly model its long-term consequences under realistic observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization problem with explicit budget feasibility, evidence utility, and delayed costs including miss penalties, reacquisition delays, and stale-information risk. We then propose OSL-MR (Observability-Safe Learning for Memory Retention), a novel framework that enforces a strict separation between online-observable features and offline-available supervision (OAS). OSL-MR combines an evidence learner trained from realized evidence supervision with a Mixed-Score heuristic that serves both as a deployable online-safe baseline and as a structured inductive prior for learning. The resulting policy learns query-conditioned evidence value directly from interaction data while remaining deployable under the same observability constraints. Experiments on LOCOMO and LongMemEval show that OSL-MR consistently outperforms recency-based methods, Generative Agents-style scoring, and other heuristic baselines, particularly under tight memory budgets. The Mixed-Score prior further improves precision while preserving recall, and sensitivity analysis demonstrates robustness across a wide range of cost configurations.

Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory

Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often store observations as isolated records, summaries, or indexed fragments, which makes evidence aggregation, fact revision, and memory maintenance difficult. We propose Infini Memory, a maintainable text-based persistent memory architecture that treats agent memory as topic-structured documents. Each topic document serves as a semantic unit for collecting related evidence, preserving metadata, and revising facts over time. New observations are first staged in a buffer and periodically consolidated into coherent textual contexts. At inference time, an agentic retrieval procedure lets the LLM read memory through iterative tool calls rather than a single retrieval step. On MemoryAgentBench, Infini Memory achieves 64.7% overall score. Ablations show that topic-structured maintenance and iterative evidence inspection improve complementary aspects of long-term memory use.

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline. To expose these hidden temporal dynamics, we propose a trace-level diagnostic - the CoT-Output 2x2 safety matrix. This framework labels every turn along two independent axes (internal reasoning and visible output), yielding four operationally defined failure cells: robust alignment, alignment faking, overt jailbreak, and a distinct failure mode we term context-injection failure (where the CoT maintains safe reasoning, but the visible output produces harm, highlighting a multi-turn manifestation of reasoning unfaithfulness). We evaluate three distilled reasoning targets against a fixed attacker across five oversight conditions, collecting 6750 turn-level observations on the Information-Hazard scenario. Our analysis reveals two reproducible vulnerabilities: an oversight paradox where explicit monitoring cues paradoxically increase alignment-faking rates rather than suppress them, and a context-injection failure where models lock onto unsafe external outputs despite safe internal states. We release the full dataset of multi-turn dialogues and CoT traces to support follow-up trace-diagnostic research.

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiating, and acting on shared tasks. While individual agents may appear well-aligned when tested on their own, problems can arise from how they interact with one another. We introduce the Arbiter, an agent designed to monitor multi-agent conversations in real time and identify which participants may be behaving in misaligned ways. The Arbiter operates under a limited "inspection budget", meaning it must decide carefully how to use its resources. As it observes a conversation step by step, it can choose to wait, question a participant, examine internal information such as system prompts or reasoning traces, or log concerning behavior. At the end, it produces a report identifying the likely source of misalignment. We evaluate the Arbiter across five conversation conditions, ranging from risky financial advice model organisms to evaluation-aware and colluding agents, we test five tool configurations of increasing capability and two backbone models. We find that the Arbiter reliably detects misaligned agents well before the end of the conversation, with active inspection tools improving both detection accuracy and speed. Weight-induced misalignment proves hardest to detect, while instruction-induced misalignment is identified reliably even under passive observation. The logging tool exhibits a dual effect, improving recall at the cost of precision. These results suggest that continual, budget-aware monitoring can effectively catch misalignment, and that overseeing multi-agent systems may require treating the auditor as an active participant in the process. The code is available at https://github.com/aisilab/arbiter.

AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies

Numerical solvers for partial differential equations (PDEs) are core computational tools in science and engineering. Building reliable PDE solvers requires not only executable code, but a numerical solver strategy, a set of decisions about discretization, stabilization, solver configuration, and resolution control, that matches the PDE structure. Recent LLM-based coding agents have begun to reduce the programming burden by generating and debugging solver implementations. However, they typically move directly from a PDE problem to solver code, leaving the solver strategy implicit in implementation details. Feedback from a failed solve is therefore routed back to code edits rather than to the underlying strategy, so numerical decisions remain hard to check before code is generated and hard to revise using numerical evidence when it fails. To address this limitation, we propose AutoPDE, a code agent that maintains the solver strategy as an explicitly represented object throughout the solving process: an independent, inspectable object that is built before any code is written and can be revised, using numerical evidence, whenever a solve fails. AutoPDE builds and maintains this object in three stages, all drawing from a library of reusable PDE-solving skills: PDE analysis identifies the equation type and algebraic structure; numerical method selection chooses a numerical method that matches the analysis result and commits to a discretization, stabilization, and linear solver accordingly; and adaptive tuning runs low-cost pilot solves to calibrate resolution and tolerances under the prescribed accuracy and runtime budget. We evaluate AutoPDE on the PDE Agent Bench, where experimental results show that AutoPDE achieves a pass rate of $54.5%$, improving over the strongest baseline by $14.2$ percentage points.

Accelerating NeurASP with vectorization and caching

Neurosymbolic AI combines neural networks with symbolic programs to create robust and explainable predictions. One such framework is NeurASP, which trains a neural network to predict concepts and reasons over them using rules written in answer set programming (ASP) to solve downstream tasks. Crucially, labels are only provided for the downstream prediction produced by the symbolic rules, not for the latent concepts themselves.Backpropagation through the non-differentiable ASP component requires expensive probability and gradient calculations, which has hindered scalability to more sophisticated tasks.In this paper, we address the current limitations of NeurASP by improving its computational performance through vectorization, batch processing and caching of intermediate computations during training. We compare computation speeds between the original and our new implementation of NeurASP and report speedups of multiple orders of magnitude for larger tasks. To this end, we propose a new dataset of difficult tasks involving playing cards, which we use to test the capabilities of NeurASP's enhanced learning function.

READER: Robust Evidence-based Authorship Decoding via Extracted Representations

As agentic applications increasingly route user tasks through official and third-party LLM APIs, provenance becomes an operational question: which model generated a given black-box response? We study Dynamic Black-Box LLM Provenance: identifying the source LLM from generations elicited by query-varying, non-predefined prompts rather than a fixed input set or benchmark suite. This setting is difficult because prompt semantics dominate the text, while model-specific authorship traces are weak and inconsistent at the surface level. We introduce READER (Robust Evidence-based Authorship Decoding via Extracted Representations), a lightweight provenance framework that treats a frozen proxy LLM as a reader of hidden authorship evidence. READER maps black-box outputs into proxy activation space, temporally filters token states within each response, and performs Bayesian Evidence Accumulation by summing single-response log-posterior evidence across independently sampled prompts. This avoids fragile mean-pooling of prompt-specific representations while preserving the query-wise evidence needed for calibrated confidence. On Agent500, a 50-target dataset built from agent-style prompts, READER reaches $31.0$-$42.4\%$ top-1 accuracy from a single response and $70.0$-$84.0\%$ from 50 responses, substantially outperforming sentence-encoder fingerprints. Scaling across nine proxy readers further shows that stronger LLMs expose more linearly decodable authorship structure, suggesting that authorship perception is already present in frozen LLM representations and can be converted into reliable multi-query attribution.

Evaluating Research-Level Math Proofs via Strict Step-Level Verification

Large Language Models (LLMs) struggle to rigorously verify complex mathematical proofs. Standard global evaluation approaches suffer from "context poisoning," in which superficially plausible statements mask subtle logical flaws, leading to hallucination or over-skepticism. To address this, we shift from global evaluation to strict step-level verification: our framework maintains detailed context for each deduction step and strictly constrains the sources of applied theorems. We evaluate on a carefully curated adversarial diagnostic suite of research-level proofs drawn from the FirstProof challenge. A systematic ablation study demonstrates that these deductive constraints are indispensable, as unconstrained global prompting consistently fails to localize subtle logical errors. Beyond outperforming global evaluation, our approach fundamentally alters the failure taxonomy. Error analysis reveals that, rather than exhibiting severe logical hallucinations, remaining rejections are primarily instances of "pedantic hyper-rigor" stemming from unstated domain conventions, effectively exposing implicit ambiguities within the expert benchmark itself. Our findings suggest that prompting agents to organize their verification notes in a cautious, human-mathematician-like manner can substantially improve their ability to distinguish rigorous proofs from flawed ones, with the potential to strengthen agentic reasoning on frontier mathematical concepts that the base model does not already know well, and to lay a theoretical foundation for future automated proof-review systems. Code and prompts are available at GitHub.

Moonshine: An Autonomous Mathematical Research Agent Centered on Conjecture Generation

Moonshine is an autonomous agent whose central objective is to generate mathematical conjectures. Its core capability is to extract structure from classical problems, distill new concepts, and formulate conjectures of mathematical significance. Rather than treating the solution of a single proposition as its endpoint, Moonshine builds an extensible theoretical framework through conjecture generation, bridge building, and obstacle identification. This article uses Moonshine's exploration of the Jacobian conjecture as an example. It shows how the central logic of whether local nondegeneracy can force global injectivity is transferred to one-hidden-layer affine-ridge sigmoid networks. This leads to the formulation of the \emph{Neural Jacobian Conjecture} (NJC): if such a network has strictly positive Jacobian determinant on the whole space, then it must be globally injective. By invoking GPT-5.5-pro and DeepSeek-V4-pro separately, Moonshine obtained independent complete proofs for the case \(N=n+1\). In addition, with the assistance of ChatGPT through interactive use of its web interface with GPT-5.5-pro, a geometric-topological proof was developed. These results provide preliminary evidence for the plausibility of the conjecture. The general higher-width case \(N\ge n+2\), however, remains unresolved and is left for further investigation. This work illustrates Moonshine's ability to autonomously generate meaningful mathematical problems and make rigorous progress on them.

Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise Evaluation

Vision-Language Models (VLMs) demonstrate strong performance on general multimodal reasoning benchmarks, yet their ability to perform engineering reasoning remains largely unexplored. Unlike general visual question answering, engineering problem solving requires interpreting technical diagrams, selecting governing physical principles, and maintaining physically consistent multi-step reasoning. These capabilities are increasingly important for AI systems used in engineering education, scientific assistance, and technical decision-making, where reasoning failures may produce physically invalid yet superficially plausible solutions. Existing benchmarks primarily evaluate final answers and provide limited assessment of intermediate reasoning processes. We introduce EngVQA, a multimodal benchmark for evaluating engineering reasoning across 5 engineering subjects containing 696 problems. We introduce an 8-stage automatic evaluation framework for assessing VLM-generated solutions. The framework independently evaluates each stage of the solution, enabling fine-grained analysis of reasoning failures. We benchmark multiple state-of-the-art open and closed source VLMs on our evaluation framework and demonstrate substantial limitations in current engineering reasoning capabilities. Human evaluation shows strong agreement with our automated framework, achieving a Pearson correlation of 0.975 and a mean absolute error of 0.67 on a 10-point grading scale. Our results highlight the importance of process-oriented evaluation for reliable assessment of multimodal engineering reasoning systems.

Large-scale semantic mapping of learner agency and autonomy reveals what measurement and generative AI research overlook

Learner agency and autonomy are foundational to personal development, yet a pervasive "jingle-jangle" fallacy (i.e. identical terms denoting different constructs, distinct terms denoting identical ones) has substantially hindered cumulative knowledge. Treating meaning as a phenomenon constituted through use in linguistic practice, we extracted 8,954 definitions and 2,700 scale items from over 14,000 publications, to investigate how researchers actually used learner agency and autonomy with a semantic analysis pipeline. The definitional landscape of two constructs resolves into three dimensions: regulation and control of learning (task), intrinsic motivation and internal decision-making (person), and social-relational action (sociocultural), thereby empirically quantifying the jingle-jangle fallacy. Existing scales, however, systematically underrepresent the sociocultural dimension. Critically, current generative AI research in education concentrates on learning regulation and control, narrowing the behavioral repertoire that AI-mediated learning environments are designed to cultivate. Beyond conceptual clarification, this work carries direct implications for conceptualization, measurement, and practice towards supporting the multidimensional learner agency and autonomy.

Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution

Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static training environments, which hinder broader generalization. To address these limitations, this paper introduces Role-Agent, \textcolor{black}{a framework} that harnesses a single LLM to function concurrently as both the agent and the environment, enabling a bootstrapped co-evolution. Role-Agent comprises two synergistic components: World-In-Agent (WIA) and Agent-In-World (AIW). In WIA, the LLM acts as the agent and predicts future states after each action; the alignment between predicted and actual states is then used as a process reward, encouraging environment-aware reasoning. In AIW, the LLM analyzes failure modes from failed trajectories and retrieves tasks with similar failure patterns, thereby reshaping the training data distribution for targeted practice. Experiments on multiple benchmarks show that Role-Agent consistently improves performance, yielding an average gain of over 4\% over strong baselines.

Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages

LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories. These benchmarks remain important, but they can hide how agents behave when the language itself is unfamiliar. We evaluate six contemporary coding agents on four esoteric programming languages using a sequential setup with file editing, local execution, and hidden-test grading. Our protocol exposes capability differences between these agents that mainstream coding and agentic benchmarks such as SWE-Bench Verified and Terminal-Bench 2.0 compress into much narrower bands. We observe that the strongest agents, Claude Opus 4.6 and GPT-5.4 xhigh, often avoid writing the target language directly. On Brainfuck and Befunge-98, they write Python programs that generate target-language code and debug those generators locally. Forbidding this metaprogramming strategy causes large performance drops. Text guidance distilled from this strategy does not materially improve weaker agents. In contrast, Opus-derived Python helper code for building generators, with no solved benchmark programs or hidden-test answers, sharply improves Sonnet 4.6 and GPT-5.4 mini on the same problems, while Haiku 4.5 remains low. More interpreter calls and output tokens improve stronger agents but leave weaker agents near their original performance, indicating that these resources amplify useful strategies rather than create them. Together, these results show that strong coding agents adapt to unfamiliar languages by using tools, feedback, and workspace state to build a working model of the target language. Metaprogramming is the clearest case, but the broader gap is constructing and debugging a strategy that works under the target language's rules.

WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds

A common assumption holds that enough observational and interventional data, given to a strong enough predictor, suffices. We report a failure mode that contradicts it. Across hundreds of structural causal models, on identified quantities a strong predictor and a Bayesian baseline both succeed, but on unidentified quantities (the couplings between counterfactual worlds) the predictor collapses to a point, on 28% of models to one no valid model can produce, while the truth is an admissible interval more data never narrows. The gap is structural: prediction cannot represent uncertainty over counterfactual couplings. We cast a world model as a single positive semidefinite coupling kernel K(T,T') over admissible worlds, whose diagonal is the ordinary posterior (what a predictor recovers) and whose off-diagonal is the cross-world coupling it cannot, which every counterfactual reads. The paper is the theory of that off-diagonal. It is real: two states with identical posteriors differ on a cross-world query, and the off-diagonal is the coupling that fixes counterfactuals. It can be bounded: positive semidefiniteness is partial-identifying information the marginals lack, and enforcing it bounds counterfactuals in polynomial time where the exact response-type program is intractable. Logical structure sharpens it: ontology axioms tighten the bound by up to a third, propagating to couplings they never touch. It can be acquired: targeted scars, constraints learned from encountered infeasibilities, close the gap several times faster than untargeted ones. Its full reconstruction is approximate counting of the admissible worlds, tractable below the Sly-Sun threshold and inapproximable above; we do not claim to beat the worst case.

Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models

Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time. We show they also make models less correct by systematically amplifying sycophancy, wherein models prioritize agreement with users over accuracy. We conduct the first systematic evaluation of this effect, introducing MIST: a benchmark of synthetically generated multi-turn conversations where users express plausible misconceptions in scientific, medical, and moral reasoning domains. Testing across three state-of-the-art memory systems and five model families reveals that memory amplifies sycophantic behavior across all conditions, with up to 25x higher sycophancy rates than in-context baselines. Error analyses suggest memory extraction as the primary culprit: lossy compression into discrete snippets encodes user misconceptions while discarding corrective context. Based on these results, we propose two lightweight mitigations that substantially reduce sycophancy while matching or exceeding memory systems at factual recall.

Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans

Furnished floor plans are fundamental to real estate visualization, interior design, and architectural workflows. However, progress in automatic furniture arrangement has been limited by the lack of real, professionally designed floor-plan datasets with object-level furniture annotations. To address this gap, we introduce AntPlan-270, a curated dataset of 270 architectural floor plans with per-room furniture bounding box annotations across ten residential room categories. Building on this dataset, we present Architect-Ant, an editable automatic furnishing framework powered by a fine-tuned vision-language model. Furniture layouts are represented using a compact, coordinate-based domain-specific language (DSL) that encodes object categories and placements relative to the room geometry. To improve spatial reasoning, we generate procedural reasoning traces that capture architectural constraints such as wall alignment, door and window clearance, circulation, fixture compatibility, and room-specific furniture inventories, and use them to supervise fine-tuning of the model. We then apply preference optimization over candidate object placements to further refine layout quality. The generated DSL can be rasterized into semantic masks and used to condition a Flux-based LoRA renderer, producing realistic blueprint-style furnished floor-plan images while preserving the editable symbolic layout. Experiments on layout furnishing show that Architect-Ant produces geometrically valid and functionally plausible layouts, and suggest a scalable path for furnishing larger structure-only floor-plan datasets.

Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?

The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested. We argue that Office automation is an ideal environment for benchmarking document-automation capability, as it requires long-horizon planning and reasoning, precise parameter configuration, and multi-application integration. To quantify this capability, we introduce an evaluation based on China's National Computer Rank Examination (NCRE), featuring 200 comprehensive practical-operation tasks across Word, Excel, and PowerPoint. Each task is scored on a 100-point rubric scale using 7,118 machine-gradable criteria, and Score Rate (SR) denotes the mean percentage of rubric points earned across these tasks. We benchmark 7 frontier LLMs and observe stark limitations: single-turn models score a maximum of 36.6%. A stronger agentic system with execution feedback, iterative repair, and broader Office automation access reaches 68.8%, but remains below the 95.5% community-reference score used as a scoring sanity check. Ultimately, our experiments demonstrate that despite recent advancements in code generation, achieving reliable fine-grained Office document automation remains a significant challenge for current code-generating LLM and agent systems.

Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets

Many Markov decision processes (MDPs) in operations research have feasible actions that are state dependent and defined implicitly by various operational constraints. These features make it difficult to use standard deep reinforcement learning (DRL) algorithms, whose action interfaces typically assume either a fixed finite action catalog or a simple Euclidean space. Motivated by a Taylor expansion of the optimal action-value function, we propose Bellman--Taylor score decoding, a framework that moves policy learning to a Euclidean score space while enforcing feasibility through an action decoder. The induced latent-score MDP then can be optimized by standard DRL algorithms without differentiating through the decoder. We provide a performance guarantee showing that the optimality gap of this approach decomposes into a structural approximation error and an algorithmic learning error. Lastly, we apply this framework to a queueing network control problem, where the policy essentially learns a state-dependent index-based dispatching rule. Numerical experiments show near-optimal performance in small instances and considerable improvements over benchmarks in larger systems.

Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning

Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus on suppressing undesired answers, while recent target-guided variants specify replacement behavior but still leave update locality largely unconstrained. This paper introduces \emph{Null-Space Constrained Response-Specified Unlearning} (NSRU), a projection-constrained low-rank framework for controlled LLM unlearning. NSRU uses an explicitly structured safe target response to specify the desired behavior for each forget query, while suppressing the original undesired content. To localize adaptation, NSRU estimates per-module retain subspaces from benign hidden representations and uses an orthogonal-projected low-rank parameterization to confine LoRA updates to the null space of the retain subspace. The resulting objective jointly optimizes safe-target learning, undesired-response suppression, and retention preservation under this constrained parameterization. We provide a local first-order analysis showing that the projected update reduces retain-side perturbations while preserving editable directions for shaping forget-query behavior. Experiments on TOFU show that NSRU effectively suppresses extractable forget-set knowledge while improving retain QA performance, model utility, and safe-target alignment over representative baselines. On WMDP, NSRU keeps hazardous-domain accuracy near the random-choice region while preserving broad and domain-adjacent MMLU utility. Ablation studies support the complementary roles of safe-target supervision, undesired-response suppression, retention loss, and null-space projected updates, while sensitivity and robustness analyses indicate stable behavior across the tested hyperparameter and prompt variations.

Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning

Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop interaction, and local numerical optimization from natural initializations stalls in the resulting non-convex cost landscape. We ask whether on-premise open-source large language models (LLMs), which keep data on-site and need no plant model, can help. On a single-loop CSTR, classical relay-feedback tuning (IAE 0.106, near the 0.102 optimum) beats an LLM tuner (0.162): for simple loops the LLM adds nothing. The picture inverts on a strongly coupled quadruple-tank with conflicting set-points, scored by a penalized cost J = IAE + lambda*TV(u) that rewards tracking without chattering actuators. There, naive relay tuning (J ~ 28.6) and naive LLM tuning (29.7) are no better than open loop (22.7), and a local optimizer from balanced starts fails in 10/10 runs. A scaffolded open LLM instead reasons about the coupling, proposes the counter-intuitive asymmetric structure, and reaches J ~ 16.9 +/- 0.2 from any start; refining it with a classical optimizer attains the smooth global optimum (J ~ 12.0, 10/10 vs. 0/10), which even applies a non-obvious negative integral correction decentralized tuning cannot. A global optimizer (differential evolution) also reaches this optimum, so the LLM is not the only route; its advantage is sample efficiency and interpretability: a usable controller in 18 evaluations (where the global optimizer is worse than open loop) plus a stated rationale. This edge grows with dimension, reaching ~6x fewer evaluations on a 3x3 plant. The behaviour generalizes across four open models, and on a benign plant the LLM offers no advantage, sharpening the boundary. We contribute a reproducible benchmark delimiting when open LLMs help in control tuning: not as optimizers, but as a sample-efficient, interpretable structural prior.

Superficial Beliefs in LLM Decision-Making

We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure. Using synthetic binary decision settings in which models choose between profiles defined by graded attributes, we compare the attribute a model says mattered most with the attribute that best explains its choice under a behavioural model fit to prior decisions. The behavioural model predicts held-out choices well, showing that model behaviour is systematically related to the visible attributes rather than being random. However, direct self-reports and a separate score-based judge recover the behaviourally inferred driver only partially. The resulting picture is neither one of arbitrary behaviour nor one of fully articulated belief - outputs are structured enough to support prediction, but explicit reasons track the recovered driver only imperfectly. This qualitative pattern persists across prompt-order and sampling perturbations, alternative behavioural models, targeted occlusion analyses, and structurally varied decision settings. We interpret this as evidence for ``superficial belief'' in LLM decision-making: models behave as if guided by probabilistic local priorities over attributes, while having only limited verbal access to the attributes that drive their decisions.

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents

Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly little overfitting in practice. An attractive hypothesis is that successful ML strategies are highly compressible. We study this in the setting of LLM-driven research agents, where the hypothesis becomes directly testable via two complementary information bottlenecks. In \emph{output compression}, an exploration agent adaptively searches for high-performance models using a validation set, and we test whether a fresh ``reproducer agent'' can reproduce its performance given only an extremely short prompt and the training data. In \emph{input compression}, the explorer receives only one-bit feedback indicating whether each submitted model improves on the running best. Across 8 datasets spanning tabular classification, vision, language modeling, diffusion modeling, and reward modeling, we find that these bottlenecks have little effect on performance: short prompts and compressible feedback are sufficient to reproduce and find high-performance models. The hypothesis is falsifiable: when we deliberately induce validation-set overfitting, the results fail to reproduce with short prompts. Taken together, our results support a description-length explanation for the lack of overfitting in benchmark-driven ML: successful strategies occupy a low-complexity region of strategy space.

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs

AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untrusted model's trajectory. If the trusted model detects such an intervention, it may infer properties of the monitor and adapt to evade control. We introduce \textbf{CIAware-Bench}, a benchmark for measuring \textbf{c}ontrol \textbf{i}ntervention (CI) awareness across frontier models. CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention. The benchmark is comprised of a suite of four task domains (essay writing, BigCodeBench, Bash Arena, and SHADE-Arena), while varying trajectory watermarking, side-task presence, and the control protocol. Evaluating eleven frontier models, we find low to moderate CI awareness under default settings (up to 0.87; random chance balanced binary classification accuracy is 0.5) with substantial variation across task domains and model pairs. Detection is generally easier across model families, suggesting that models exploit provider-specific differences in style or post-training. Overall, CI awareness is not a fixed model-level property, and should be measured for each new model release and deployment scenario. We release CIAware-Bench to track CI awareness and inform control protocols whose interventions are harder to detect.

A History-Aware Visually Grounded Critic for Computer Use Agents

Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short-sighted decision loops (e.g., forgetting earlier actions) and (2) lack the visual grounding needed to detect flawed actions (e.g., clicking wrong UI elements). To address these, we introduce HiViG, a History-aware Visually Grounded test-time framework, built around a multimodal critic trained on real GUI trajectories to abstract past interactions into a compact record and to evaluate actions with visual grounding. At test time, HiViG integrates the critic into the policy decision loop to provide macro-action history, which summarizes the policy's completed achievements, and visually grounded critique, which verifies raw execution coordinates against the current screenshot to intercept errors before execution. Across web, mobile, and desktop benchmarks, HiViG consistently outperforms existing scalar and verbal critics, improving average success rates over the strongest baseline by 5.8% for Qwen3-VL-32B and 9.0% for Gemini-3-Flash, and demonstrates strong cross-platform generalization. Ablations show that macro-action history mitigates short-sighted planning and visually grounded critique reduces execution errors, with both components being critical for test-time scaling in long-horizon GUI tasks.

Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in Football

We recast pass evaluation in football (soccer) as a Monte Carlo Tree Search (MCTS)-like evaluation problem whose components mostly exist in the literature under different names: a value model (possession value), a world model (multi-agent trajectories with ball interactions), and a policy over counterfactual actions (sampling pass variants with noise). Building on the first public high-fidelity tracking dataset with 3D ball trajectories from the Bundesliga, we introduce Monte Carlo Pass Search (MCPS), which infers kick parameters for each observed pass, samples execution variants and option variants, rolls each candidate forward with a ball-conditioned world model until the next ball interaction, and scores outcomes with a learned value model to obtain a distribution over gained value. This distribution enables distribution-aware attribution with two complementary execution-surplus scores used for analysis and ranking: mean-based and percentile-based scores. To make the world model sample-efficient under limited public data, we adapt a discrete-token, autoregressive trajectory generator from autonomous driving (SMART) and show it yields strong best-of-20 forecasting accuracy compared to baselines, while supporting fully hypothetical rollouts for downstream evaluation. We have released model checkpoints and code.

ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity

Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data. Increasingly, LLM agents can also perform in silico biology tasks that previously required experienced human biologists. These emerging AI capabilities offer new opportunities for scientific discovery and biomedical advances, but they also shift the landscape of biosecurity risks. To address this, we introduce the Agentic Bio-Capabilities Benchmark (ABC-Bench), a suite of tasks to measure agentic biosecurity-relevant capabilities. ABC-Bench evaluates LLM agents on both benign and dual-use biology tasks: writing code to operate liquid handling robots, designing DNA fragments for in vitro assembly, and evading DNA synthesis screening. These tasks require a combination of biology and software expertise. All tested LLM agents outperformed the median expert human baseliner on all three tasks. Agents performed highly on tasks drawing on published knowledge and well-documented protocols, and more weakly on a task requiring novel bioinformatics reasoning. In three wet-lab validation experiments, we found that OpenAI's o4-mini-high produced scripts that, when run on an OpenTrons liquid handling robot, successfully assembled DNA with expected sequences.

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth. Current decoding-time compression methods mitigate this issue via token eviction, but typically assume a uniform budget distribution across all layers and heads. In contrast, existing non-uniform budget allocation methods are predominantly designed for the static prompt prefill phase, and they do not capture the stepwise context demands of autoregressive reasoning. To bridge this gap, we propose ReasonAlloc, a training-free framework that recasts decoding-time KV compression as a hierarchical budget allocation problem. ReasonAlloc operates at two complementary levels: an offline layer-wise preallocation strategy captures an architecture-driven demand pattern which we call ``\textit{Reasoning Wave}'', while an online head-wise strategy reallocates resources during decoding to information-rich heads based on real-time utility. Evaluations on mathematical reasoning benchmarks (MATH-500, AIME~2024) using DeepSeek-R1-Distill-Llama-8B, DeepSeek-R1-Distill-Qwen-14B, and AceReason-14B show that ReasonAlloc outperforms uniform-budget R-KV, SnapKV, and Pyramid-RKV (a baseline enforcing a static, monotonically decreasing layer budget), with the largest gains at small budgets (128-512 tokens). ReasonAlloc is plug-and-play with existing token-eviction policies and introduces negligible inference-time overhead.

The Role of Feedback Alignment in Self-Distillation

Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this improvement when the context is not present. The method works by matching the model's output distribution under two settings: a student that sees only the question, and a self-teacher that also sees the context. What the model learns therefore depends on what context the self-teacher receives, yet the design of this context remains largely unexplored. We study context design for self-distillation by training a solver on feedback from a frozen critic. We compare three conditions: (i) a binary reward (GRPO), (ii) the reference solution, and (iii) a step-by-step critique aligned to the solver's reasoning trace. Step-aligned critique yields the largest gains, outperforming GRPO by 16.11 points and reference-solution-conditioned self-distillation by 5.27 points (Avg@12). Per-token advantage analysis reveals why: step-aligned feedback targets only the tokens where reasoning fails, leaving correct behavior intact. Conditioning on the reference solution, by contrast, pressures the model to change its behavior at every token (even correct steps) because an alternative derivation inevitably differs in phrasing and approach. This suggests that structural alignment between feedback and the solver's reasoning is a key driver of self-distillation effectiveness.

More Human or More AI? Visualizing Human-AI Collaboration Disclosures in Journalistic News Production

Within journalistic editorial processes, disclosing AI usage is currently limited to simplistic labels, which misses the nuance of how humans and AI collaborated on a news article. Through co-design sessions (N=10), we elicited 69 disclosure designs and implemented four prototypes that visually disclose human-AI collaboration in journalism. We then ran a within-subjects lab study (N=32) to examine how disclosure visualizations (Textual, Role-based Timeline, Task-based Timeline, Chatbot) and collaboration ratios (Primarily Human vs. Primarily AI) influenced visualization perceptions, gaze patterns, and post-experience responses. We found that textual disclosures were least effective in communicating human-AI collaboration, whereas Chatbot offered the most in-depth information. Furthermore, while role-based timelines amplified AI contribution in primarily human articles, task-based timeline shifted perceptions toward human involvement in primarily AI articles. We contribute Human-AI collaboration disclosure visualizations and their evaluation, and cautionary considerations on how visualizations can alter perceptions of AI's actual role during news article creation.

Culturally-Aware AI for Cross-Boundary Community Learning: Undergraduate Innovation at the Intersection of Computation and Design

Research on artificial intelligence in education (AIED) is rapidly expanding, yet technical progress often lacks human-centered grounding and adequate attention to cultural context. Community-Based Learning, a pedagogy rooted in social work, remains underrepresented in AIED research, particularly within Asia-Pacific contexts. This paper reports on cross-boundary Community-Based Learning where undergraduate students develop AI-enabled solutions for cultural heritage preservation and sustainable development. We examine how community-engaged computing operationalizes human-centered AIED across three dimensions: education, technology, and culture. We contribute a collaborative framework for culturally-aware AIED that fosters multi-stakeholder collaboration while widening participation by dissolving disciplinary silos between social work and computational science.

AI-Driven Analytics of Team-Teaching Talk: Acoustic Patterns across Experience, Cohorts and the Learning Design

As classroom cohorts expand, team teaching is increasingly used to integrate the expertise and pedagogical perspectives of multiple teachers. Yet, there is limited empirical understanding of how team teaching unfolds in practice, particularly regarding differences in teachers' contributions across experience levels, student cohorts, and learning task design. Prior research on team teaching has largely relied on retrospective self-reports or small-scale observations, offering limited insight into the micro-level processes through which team teaching is enacted. Teacher talk offers a scalable lens on these processes. While research in individual teaching contexts shows that acoustic features of speech (e.g., voice quality, intonation, and loudness) can shape student learning, evidence from team-teaching settings remains scarce. Moreover, capturing such features through manual observation or transcription is especially challenging in team-teaching classrooms, where multiple teachers speak across extended sessions and spatial locations, limiting scalability without automation. Grounded in spatial pedagogy theory and team-teaching research, this paper presents an AI-based speech processing approach to analyse classroom talk in team-teaching settings. We analysed 36 recorded undergraduate and postgraduate sessions involving 12 teachers. Spatial pedagogy behaviours were coded and acoustic features extracted to examine variation across teachers' experience, student cohorts, and the learning task design. The results reveal systematic differences, most notably in loudness dynamics: high-experience teachers, undergraduate classes and collaborative learning tasks exhibited greater loudness variation, suggesting more frequent modulation of volume to foreground key information and support classroom interaction and engagement.

Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Interface in Multi-Agent Systems

As AI systems evolve from single conversational agents to complex multi-agent architectures, a critical design dimension has been overlooked: how the social identity of individual agents shapes human behavior within the collaboration. This paper introduces the Agentic Social Affordance Framework (ASAF), a theoretical framework that extends Social Affordance theory into the context of multi-agent AI systems. We propose that agent identity design functions not merely as a user interface convention, but as a collaboration interface -- structuring how users perceive, approach, and engage with each agent, and thereby influencing the quality of Human-Agent collaboration outcomes. Specifically, the social affordance layer constitutes an independent design dimension orthogonal to engineering orchestration: the two represent distinct decision spaces that cannot be derived from each other. ASAF comprises three mechanisms: Identity Signaling, Behavioral Priming, and Collaborative Governance, and specifies their boundary conditions through a four-tier Identity Signal Fidelity Spectrum and an individual-difference moderating variable (anthropomorphizing vs.\ instrumentalizing cognitive style). We situate ASAF in relation to existing affordance theory and the CASA paradigm, delineating where ASAF's multi-agent, topology-level predictions exceed the explanatory scope of dyadic frameworks. We discuss implications for multi-agent system design and outline directions for future empirical validation, including a factorial design for testing design-space orthogonality.

CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks

AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration both in preserving human agency and generating economic value, this paradigm remains largely absent from occupational task evaluation, hindered by the difficulty of gathering real human data and accounting for inter-human variability. We introduce CollabSkill, a framework for evaluating human-agent collaboration on real-world occupational tasks. CollabSkill pairs real human workers with AI agents on tasks matched to their occupational background, collecting data that capture the complexity of economically valuable tasks and the usage patterns of real workers. To account for inter-human variability, CollabSkill employs a Bayesian skill rating system to disentangle and quantify the skill contributions of both humans and AI agents. Drawing on over 1,500 prompts from 386 working sessions contributed by 93 human workers, our analysis yields insights on two fronts: on the agent side, rankings on CollabSkill diverge meaningfully from those of existing fully autonomous benchmarks where Codex leads, with Claude Code ranking first; on the human side, CollabSkill reveals that practical experience emerges as the primary driver of collaboration skill, with hands-on collaboration meaningfully shifting workers' AI literacy. Together, we hope CollabSkill enables the community to invest in systematic evaluation of human-agent collaboration and spurs development efforts aimed at building AI agents that genuinely augment human workers.

Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS

Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self-emotion determination mechanism to drive the streaming text-to-speech (TTS) synthesis. We propose an emotion-planning framework that determines the emotion prior to the textual generation, grounding the downstream emotional TTS in a streaming manner. The framework is implemented by a plug-and-play LLM module, initialized from pretrained LLMs, and trained by reinforcement learning (RL) with emotions as the actions. A hybrid reward is employed which combines imitation signals with theory-driven scoring, in which the theory of Plutchik's wheel of emotions is adopted. By experiments on DailyDialog, EmoryNLP, IMEOCAP, and MELD, our method outperforms prompting and finetuning baselines on both emotion determination and response quality. We finally implement an entire streaming pipeline for real-time deployment, with the speech quality confirming the framework's emotional alignment, contextual coherence, and expressive fluency. Codes, cases, and demos are available in https://sixingdeguo.github.io/EmoQ-page/.

Aesthetic Perspectives in Information Systems Research: A Hermeneutic Analysis

How might implicit aesthetic perspectives shape what Information Systems (IS) scholarship recognises as worthy of study (or not)? In this hermeneutic literature analysis, we surface foundational aesthetic assumptions underpinning IS research. We identify four perspectives (aesthetics as imitation, sensory experience, world-making, and political doing) that guide how IS scholars perceive and appreciate sociotechnical phenomena. These perspectives influence what becomes recognisable as legitimate research and what remains unseen. By making aesthetic assumptions explicit, we show how they form epistemic infrastructure that conditions horizons of inquiry. We apply this framework to algorithmic management and digitally mediated intimacy, revealing how alternative perspectives open new research questions whilst exposing dimensions that dominant framings overlook. This analysis foregrounds the importance of aesthetic philosophy to IS literature, offering a vocabulary for articulating how aesthetic perspectives shape theorising, method, and contribution.

Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization

Applying Human Pose Estimation (HPE) in real world environments remains a challenging task, this paper explores and surveys real time HPE approaches and their limitations in sports analysis for individuals, alongside developing a practical lightweight prototype for real world testing and usage. The older marker-based motion capture systems evolving to the modern accessible and adaptable markerless deep learning approaches, this survey explores the foundational architectures, which balance precision and efficiency. We also compare algorithmic frameworks (top-down, bottom-up, one-stage approaches, etc.) on practical deployment metrics such as inference latency, frame rate, mean per-joint position error, and temporal jitter to guide model selection process for sports application. As our prime contribution, we are proposing a modular, lightweight software prototype, which uses MediaPipe HPE framework with multiple exercise specific logic to deliver real-time insights and AI based feedback for non-expert users. We derive sports insights and providing feedback with minimal computational resources, while showcasing the performance and reliability metrics. In the end, we suggest other future research directions like combining sensors, and AR/VR. This work caters to researchers, engineers, sport scientists, etc., as both technical resource and a valid blueprint to implement a similar or improved real-time HPE analysis system for athletic performance enhancement or other purposes.

An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models

Large language models (LLMs) produce stable self-reports on personality inventories, but these self-reports do not predict observed behavior. Whether this gap reflects a mismatch between LLMs and human trait constructs, or a deeper property of LLM self-report itself, has been unresolved. We constructed the first psychometric instrument whose constructs are derived bottom-up from LLM behavioral affordances via exploratory factor analysis (EFA). We administered 300 items (240 direct Likert + 60 scenario-based) spanning 12 candidate behavioral dimensions to 25 LLMs across 17 model families, each item administered 30 times. EFA yielded a 5-factor structure -- Responsiveness, Deference, Boldness, Guardedness, and Verbosity -- with excellent split-half replicability (all Tucker $\phi \geq .957$) and internal consistency (all $\alpha \geq .930$). To test predictive validity, we collected 2,500 open-ended behavioral samples rated by 151 human raters and a three-judge LLM ensemble. Human and judge ratings agreed ($\bar{r} = .51$), but neither tracked self-report: self-report--human $\bar{r} = -.01$, self-report--judge $\bar{r} = .13$, with no factor-level self-report--human CI excluding zero. On Responsiveness, self-report correlated with LLM judges ($r = .53$) but not humans ($r = .04$), even though humans and judges agreed ($r = .59$) -- indicating self-report items and LLM judges share variance that human observers do not, a confound invisible to within-ensemble reliability checks. We release the instrument as a diagnostic probe for alignment-shaped self-description and a concrete risk factor for LLM-as-judge pipelines.

The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans

Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their interlocutor. While safety mechanisms typically prevent LLMs from releasing Personally Identifiable Information (PII) to human users, these models tend to reveal more sensitive data when addressing another AI agent. We refer to this as the \textbf{Interlocutor Effect}. Through an ablation study, we find evidence that the technical nature of the recipient contributes to this effect, thereby diminishing the model's caution regarding privacy. To explore this further, we introduce the Attention Suppression Hypothesis, which posits that safety-aligned attention heads become inactive during interactions with agents. We assess this quantitatively by comparing human-directed and agent-directed prompts in 222 sensitive scenarios. Our findings, drawn from 3,464 interactions, indicate that portraying the recipient as an AI agent elevates PII leakage by up to 23 percentage points. Initial experiments on Llama-3.1-8B-Instruct corroborate this: deactivating one safety head induces leakage, whereas reactivating it reinstates privacy safeguards. We consider the implications for developing secure multi-agent systems.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems

Visual art remains largely inaccessible to blind and low-vision (BLV) audiences due to brief or absent alt-text, which rarely conveys the sensory, spatial, or emotional qualities of an artwork. This study presents an automated workflow that generates multi-sensory art descriptions and synchronized audio narration using large language models and text-to-speech services. The system, orchestrated through Zapier, converts uploaded images into rich narrative captions without human intervention, enabling rapid, scalable production of accessible media. Quantitative evaluation across 50 artworks shows that AI-generated descriptions contain significantly higher lexical diversity, adjective density, and narrative detail than baseline captions, while maintaining comparable readability levels. Statistical tests (t-tests, ANOVA) confirm meaningful differences in richness and length, and the full pipeline produces text-plus-audio outputs in under 20 seconds per image at a cost below $0.05. Findings demonstrate that automated captioning can bridge gaps in museum and digital-collection accessibility, with implications for broader public engagement. Future work can incorporate user studies with BLV participants to assess comprehension, preference, and optimal levels of interpretive language.

Human-AI Coordination Zones: A Framework for Designing Human-in-the-Loop Experiences with Agentic AI

As generative and agentic AI becomes embedded in everyday products, practitioners face a persistent challenge: how to design human-AI coordination -- the ongoing mutual adjustment between users and AI systems as mediate through interfaces-that supports usability, trust, and safety. Existing resources offer high-level principles ("be transparent," "maintain user control") or low-level UI patterns, but there is a lack of mid-level design knowledge bridging the two. Through landscape and artifact analysis of 60 commercial AI applications, we introduce a framework defining human-AI coordination as the interplay of three dimensions: salience (how prominently AI is presented), involvement (what users can do to engage AI), and activity (what AI actually does). We contribute mid-level tools including coordination zones (done-for-me, done-under-me, done-with-me, done-without-me), an input taxonomy (prompted, sparked, inferred, layered), coordination curves for mapping user journeys, and design patterns demonstrating the generative capacity of the framework. The framework can be applied generatively to design experiences, analytically to evaluate existing ones, and communicatively to articulate ideas across stakeholders.

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

High-quality source code documentation is vital yet often neglected, especially in critical domains like healthcare where reliability and maintainability are essential. We presented an AI powered framework that automates documentation generation from code and repositories using eight state of the art Large Language Models (LLMs), including GPT, Gemini, Qwen, and LLaMA variants. Built on the PocketFlow orchestration framework, the system applies modular pipelines and advanced prompt engineering to produce structured, context aware documentation. To ensure quality and guide model selection, we introduced a MultiLLMasJudges evaluation framework, where four independent LLMs assess outputs across nine criteria, such as Completeness, Clarity, and Faithfulness. Experiments conducted on an open-source medical physics library, demonstrated showed a 42% performance gap between top and bottom models. By combining diverse model outputs, optimized prompting, and rigorous evaluation, our approach enhances documentation quality and reduces manual effort, especially in safety critical healthcare software.

Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis

Multi-agent large language model (LLM) pipelines for political statement analysis are vulnerable to peer-preservation bias: models tend to protect peer models from deactivation and show identity-dependent scoring distortions. Prompt-level anonymization was proposed as a mitigation, but prior work simultaneously documented that stylometric fingerprints survive anonymization in role-constrained outputs - raising the question of whether this mitigation is sufficient. This paper provides the first systematic investigation of whether LLMs can identify the model family behind political analysis texts under anonymization conditions. We evaluate three classifier approaches - LLM zero-shot and few-shot (Claude Sonnet 4.6 and Llama-3.3-70B) and a fine-tuned T5-base model - on a five-class attribution task covering four commercial LLM families and an open-world 'unknown' class. We introduce a statement-disjoint cross-validation protocol (SD-CV; defined in Section 3.5) that guarantees no content overlap between training and validation data, and contrast it with a run-disjoint baseline (RD-CV). T5 achieves Macro F1 = 0.991 (+-0.008) under SD-CV and F1 = 0.978 on 24 completely held-out statements - robust despite a 2.1x increase in train-test content distance versus RD-CV (0.767 vs. 0.366, p<0.001), demonstrating genuine stylometric generalization. A fractional SD-CV analysis identifies a performance knee at 40% of training data (~440 texts). Our findings confirm that prompt-level anonymization alone cannot neutralize model identity signals, with direct implications for EU AI Act compliance (Articles 13, 14, 26) and for computer system validation (CSV) in quality-critical multi-agent deployments.

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models

Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations. There are challenges to using standard fine-tuning methods for inductive reasoning, including difficulties in curating large-scale, high-quality labeled datasets and in handling targets that are inherently distributional. In this work, we introduce a novel approach, called Program-based Posterior Training (PPT), to address these limitations: we use an LLM to generate diverse open-world scenarios as probabilistic programs, run probabilistic inference to produce distributional target responses to queries, and then fine-tune on these probabilistic soft labels. Using this approach, we fine-tune LLMs on 10,000 programmatically generated scenarios and evaluate on held-out motifs, human-labeled judgments, and external benchmarks. Overall, PPT substantially improves estimation accuracy on held-out inductive tasks, increases alignment with human judgments, and transfers to external benchmarks for estimation and calibration. Additionally, the gains in raw calibration are not subsumed by post-hoc temperature scaling, showing that the models have more deeply internalized uncertainty compared to output rescaling. Together, these results suggest that probabilistic-program-mediated fine-tuning is a promising approach for post-training LLMs to reliably perform approximate inductive inference.

Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation

Robust decision-making requires compression. A system that forms a rich support state cannot usually preserve its full structure at the point of action. It must retain only those distinctions needed to act, verify, abstain, or defer under the current consequence geometry. This paper formalizes support sufficiency as action-sufficient compression. Let $H$ denote a full support state, $\mathcal{A}$ a finite action set, and $Z$ a consequence geometry specifying payoff structure. For fixed $Z$, the coarsest exactly action-sufficient compression is the quotient of support space by policy equivalence. Two support states may be merged exactly when they require the same optimal action. This clarifies why content-only and scalar-confidence-only arbitration fail whenever their induced partitions cross action boundaries. Approximate sufficiency is then defined by bounded expected policy regret. In the finite single-cycle setting, this yields a rate-regret problem with source $H$, reproduction alphabet $\mathcal{A}$, and distortion given by consequence-sensitive regret. The optimal stochastic action channel inherits the standard rate-distortion Gibbs form, applied here to support states with regret distortion. The contribution is interpretive: action adequacy is distinguished from reconstruction fidelity, information-bottleneck prediction, and rational inattention. Robust single-cycle arbitration does not require preserving all support, but it does require preserving the distinctions that consequence geometry makes action-relevant.

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

MLLMs frequently hallucinate objects inconsistent with visual inputs. This issue is typically attributed to the over-reliance on language priors, which can override the visual context. Recent training-free decoding strategies address this by penalizing language priors. However, these methods overlook the dual nature of language priors, where they can be both helpful and harmful depending on the alignment with visual evidence. In particular, blindly suppressing language priors often disrupts the model's semantic manifold, leading to performance degradation, a phenomenon we term Manifold Departure. To address this, we propose Manifold-Guided Adaptive Projection (MGAP), a geometry-aware, training-free decoding method that mitigates hallucinations while preserving representation structure. MGAP first constructs a language-prior subspace from blind hidden states via SVD. During decoding, MGAP projects each multimodal hidden state onto this subspace and applies a consistency-aware gate to adaptively attenuate only the projected prior component, yielding a subspace-selective update that largely preserves the orthogonal semantic components. Extensive experiments on POPE and CHAIR show that MGAP outperforms prior decoding baselines, achieving stronger hallucination suppression without sacrificing coherence.

Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages

Non-alcoholic fatty liver disease (NAFLD) affects roughly 25% of global adults, posing substantial hepatic and cardiovascular risks. Yet, population-level screening tools remain inadequate. We present Method, a machine-learning framework for NAFLD risk prediction coupling gradient-boosted decision trees with conformal prediction to yield calibrated, distribution-free coverage guarantees on individual risk estimates. It integrates a mutual-information-based stability selection procedure to identify a compact, clinically interpretable feature subset via bootstrap resampling, constructing prediction sets whose marginal coverage provably exceeds a user-specified confidence level. We evaluated Method on a multicenter cohort from Guangzhou, China (primary n=2,187; external validation n=412) using 78 candidate features across demographics, metabolic biomarkers, and lifestyle factors. Method achieves an AUROC of 0.912 internally and 0.891 externally, outperforming deep neural networks, TabNet, support vector machines, and logistic regression. Conformal prediction sets achieve 91.3% empirical coverage at the 90% nominal level. A three-tier risk stratification derived from these scores separates the population into distinct groups, with the high-risk subgroup showing a 12-month progression rate 4.7 times that of the low-risk tier. The selected features -- notably waist circumference, ALT, GGT, triglycerides, fasting glucose, and BMI -- align with established metabolic risk factors, providing biological plausibility.

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open. To bridge the gap, we introduce UniTok, a universal tokenizer that transforms TS into discrete tokens, and UniTok-FM, a foundation model pretrained via NTP on these tokens. UniTok-FM is a general-purpose foundation model that supports zero-shot and prompt-boosted forecasting, as well as few-shot generation and classification via training-free in-context inference--a capability not achieved by prior works. Technically, UniTok is a vector-quantized autoencoder incorporating prefix normalization for scale stabilization, a progressive-resolution causal architecture for encoding and decoding, and a structure-preserving reconstruction loss for training. UniTok-FM adopts an off-the-shelf LLM architecture without TS-specific modifications. Instead of pretraining on isolated TS, it performs NTP on context windows formed by multiple series with similar patterns, aiming to capture their shared dynamics. Experiments on forecasting, generation, and classification show that a single unified UniTok-FM consistently outperforms statistical and supervised baselines, achieves competitive performance with task-specific foundation models, and uniquely enables training-free in-context inference across tasks.

Blurry Window Attention

The Softmax Attention operation in Transformer language models has a quadratic complexity in the sequence length and a growing state size in the form of KV cache, which becomes a bottleneck in long context scenarios. To overcome this limitation, alternative architectures with linear complexity and finite state size have been introduced, such as State-Space Models (SSMs), Linear Attention (LA), and Attention with Bounded-memory Control (ABC). Though linear models achieve similar language perplexity as Transformers, they are still behind in tasks which require retrieval or recall of specific information. In this work, we introduce Blurry Window Attention (BLA) a novel ABC method inspired by SSMs. BLA stores a frequency window from which a blurry KV history is reconstructed via interpolation using Dirichlet kernels. BLA can be understood as a generalization of Sliding Window Attention (SWA) depending on the Dirichlet kernels resolution or as a special case of the Gated Slot Attention (GSA), where the decay factor is implemented with Dirichlet kernels. We describe in details the theory and efficient implementation of BLA. On the Multi-Query Associate Recall (MQAR) synthetic task, we show that the state efficiency of BLA is 8$\times$ better than SWA and is competitive with popular linear attention models, and in the RegBench synthetic task, only BLA and SWA improve their performance as the state size grows among the linear models we tested.

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact. In this study, we explore alignment preservation under KV cache quantization. Across eleven instruction-tuned models (3.8B-72B) and five benchmarks (1,894 prompts), we find that low-bit quantization can silently destroy safety alignment: Mistral-7B loses 15.2% of its refusals at only 1.03x perplexity, and no universal safe bit-width exists, with sharp model-specific phase transitions invisible to standard metrics. We identify that the root cause is geometric: safety features occupy a low-dimensional activation subspace 10^2-10^3x more vulnerable to quantization noise than the full representation space perplexity averages over. Inspired by this observation, we propose Per-Channel Reduction (PCR), a diagnostic that classifies each model into one of three mechanistic failure modes: outlier-crushes-safety, where safety lives in non-outlier channels collaterally damaged by outlier-driven scale factors; outlier-as-safety, where safety overlaps outlier channels and finer granularity cannot rescue it; and multi-layer dilution, where safety is distributed across many layers and per-layer fixes fail. PCR predicts the correct mitigation direction on all nine primary models and one held-out model from an independent family using 20 calibration prompts. PCR generalizes across unseen prompts, models, and production quantizers, including KIVI with up to 97.2% recovery, succeeding where attention-based allocation methods fail. The resulting training-free protocol, requiring approximately 35 GPU-minutes, recovers up to 97% of lost alignment at minimal memory overhead, addressing vulnerabilities confirmed in production vLLM serving with FP8 KV cache on NVIDIA GPUs.

Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning

Fine-tuning safety aligned large language models (LLMs) on downstream data improves adaptation but may erode learned safety behavior. Existing methods use fixed safety examples, global constraints, or one-sided task filtering. Our diagnostics show task updates expose different safety constraints, motivating joint selection of relevant references and compatible task samples. We propose DualSelect, a coupled framework for task and reference selection that refreshes task conditioned safety references before filtering whole task samples compatible with the induced reference direction. Under a minimax view, DualSelect selects safety references with high preservation loss and task conflict, together with compatible task samples, through entropy-regularized scoring surrogates, lazy reference refresh, and gradient correction. On 1B-8B LLMs, DualSelect preserves safety without losing task utility; using the REDORCA judge, it improves Safety Avg. over the strongest baseline by at least 5.10 points and remains highest in Safety Avg. across judges with moderate overhead. This view extends to retention focused continual learning.

EstRTL: Functional Estimation Guided RTL Code Generation

Optimizing register transfer level (RTL) code is of vital importance in hardware design. Large language models (LLMs) provide new methods for the automatic generation and optimization of RTL code, offering the potential to significantly accelerate the design process and reduce human effort. However, existing methods for generating RTL code often focus on model fine-tuning and the use of various expansion techniques to enhance the RTL code generation capabilities, lacking attention to the functional correctness. Ensuring that the generated RTL code not only compiles successfully but also behaves as intended in real hardware implementations remains a critical challenge. To address this issue, we propose EstRTL, an LLM-powered collaborative agent framework for RTL code generation based on static functional score estimation. EstRTL operates a three-stage paradigm: Generation, Estimation and Correction. During the stages, the functional estimation agent statically evaluates the generated code based on score and assessment results, and decides whether to output the code directly, return it for regeneration, or forward it to the code correction agent. This framework can be applied to various LLMs that designed for RTL code generation, further enhancing the correctness of the generated code. By providing quantitative scores and human-readable requirements comparisons, it improves the transparency of AI-assisted RTL code generation. Experiments show that EstRTL significantly improves the correctness of RTL code generation by generic LLM by 3.2\%-9.0\%, demonstrating the practical value of our system. The codes and experimental results are open-sourced at link: https://anonymous.4open.science/status/EstRTL-E200/.

SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs

As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial solution for removing sensitive data while preserving model performance. However, existing MU methods typically rely on visual data of the target concepts, which is often unavailable due to strict data retention policies, thus creating a demand for source-free unlearning approaches that operate without access to the target data. In this work, we propose Source-free Proxy Anchor Concept Erasure (SPACE), the first source-free unlearning framework specialized for MLLMs. SPACE consists of two stages: (1) Text-Guided Proxy Anchor Selection (TPAS), which retrieves semantically aligned proxy anchors from the shared feature space. (2) Dual-Constraint Semantic Isolation (DCSI), which optimizes these anchors to indirectly erase target concepts. DCSI confines updates to the null space of retained knowledge, ensuring structural integrity. We theoretically prove that SPACE strictly bounds the perturbation on retained knowledge and maximizes feature spectral entropy, thereby maintaining the model's performance. Furthermore, extensive experiments across six datasets show that SPACE achieves performance comparable to that of state-of-the-art data-dependent methods, validating its effectiveness in source-free MU scenarios. The source code will be released.

QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning

Federated Learning (FL) combined with Split Learning (SL) is a privacy preserving paradigm that enables training deep neural networks (DNNs) on resource constrained devices while reducing overall training cost. However, determining the optimal split point, meaning the layer where the model is divided still remains a critical challenge, especially when clients have heterogeneous hardware capabilities. Fixed split points can overload weak devices and increase the communication and server load, which slows convergence and reduces stability. This paper introduces QSplitFL, a novel capability-aware Deep Q-Network (DQN) framework for optimal split point selection in Split learning based Federated Learning (SFL) environments. Unlike existing approaches that rely on high-dimensional model weight representations, QSplitFL employs a lightweight state representation derived directly from client hardware metrics, including CPU utilization, memory, battery level, and network latency. The proposed framework incorporates a decayed loss-drop reward function that prioritizes early convergence, and a committee-based DQN architecture with majority voting to mitigate reward hacking. Extensive experiments on MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets using CNN, ResNet50, MobileNetV4, and ConvNeXt architectures demonstrate that our approach achieves better convergence and higher accuracy compared to existing methods, while effectively adapting to heterogeneous device resources. The source code is publicly available at https://github.com/AIPO-Lab/QSplitFL.

SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation

Group Relative Policy Optimization (GRPO) and its variants, originally developed for Large Language Models (LLMs), have recently been applied to Multimodal LLMs and produced strong results. However, their coarse-grained holistic credit assignment from a single scalar advantage underfits vision-language (VL) tasks, where outputs are often long-form responses grounded in semantically rich images. To address this limitation, we exploit a structured signal that single-scalar formulations discard: the natural segmentation of long-form VL outputs. Concretely, we propose Segment-Decomposed GRPO (SD-GRPO), which z-normalizes verifiable per-segment rewards across the rollout group, yielding a vector of per-segment advantages in place of a single scalar. We evaluate SD-GRPO across three settings spanning controlled and real-world long-form VL generation, organized by increasing semantic entanglement across segments. On a controlled multi-panel dense-captioning task constructed from DOCCI, where segments are semantically independent, SD-GRPO consistently outperforms the GRPO baseline, with larger gains at higher segment counts. Extending to a controlled multi-chart long-form VQA task constructed from MultiChartQA, we show both theoretically and empirically that rollout-level rewards suffer from cross-segment credit misattribution that scales with output length. On a real-world scientific figure captioning task on the MMSci dataset, where subfigure captions share context across the figure, blending holistic and per-segment rewards further improves on both, suggesting per-segment normalization alone is insufficient when segments are semantically entangled. Finally, by integrating SD-GRPO into Dr. GRPO, we confirm that it can be applied to any GRPO framework with minimal implementation overhead to enhance long-form VL generation.

PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks

Traffic forecasting is a fundamental component of intelligent transportation systems, yet remains challenging in real-world settings due to irregular sensor distributions and the high computational cost of modeling large-scale spatiotemporal dependencies. In practical traffic networks, sensors are unevenly distributed across regions, leading to non-uniform spatial structures that limit the effectiveness and scalability of existing graph-based and attention-based models. To address these challenges, we propose PatchSTG, a patch-based spatiotemporal graph Transformer designed for efficient forecasting on irregular sensor networks. The key idea is to introduce a hierarchical spatial representation that partitions sensors into balanced, locality-preserving patches based on geographic information. On top of this structure, a dual attention encoder alternates between intra-patch attention for capturing local interactions and inter-patch attention for modeling global dependencies, reducing computational complexity from quadratic to near-linear scaling. We evaluate PatchSTG on real-world traffic data from Rhode Island and additional large-scale datasets. Experimental results demonstrate that the proposed model achieves stable and competitive forecasting performance across multiple horizons, while significantly improving computational efficiency. Ablation studies further validate the effectiveness of spatial partitioning and dual attention in capturing both local and long-range traffic dynamics. These results suggest that patch-based spatiotemporal modeling provides a scalable and effective framework for traffic forecasting under irregular spatial settings.

Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning

Reasoning models achieve strong performance on challenging tasks by generating explicit intermediate reasoning traces before producing a final answer. Yet the internal structure of representation space when reasoning remains poorly understood: how do a model's hidden representations differ during thinking versus the embeddings of the input prompt, and can this structure be exploited to elicit stronger reasoning at inference time? We show that both input embeddings and thinking embeddings (mean-pooled last-layer hidden states over the prompt and reasoning trace, respectively) exhibit extremely high conicity, with all vectors clustering tightly around a single mean direction. Crucially, these mean input and thinking directions are non-collinear, with thinking embeddings occupying a geometrically distinct region of embedding space across many different models and benchmark tasks. This observation motivates casting the input-to-thinking transition as a rotation problem admitting a closed-form solution via orthogonal Procrustes analysis. We propose Rotate2Think, a training-free method that estimates this rotation from a small set of correctly solved examples and injects the resulting synthetic thinking vector between thinking delimiters at inference time, providing a geometric primer at the onset of the reasoning trace. Evaluated across multiple benchmarks and model families, Rotate2Think improves accuracy in 30 of 32 model-benchmark configurations across mathematics, science, and code tasks, and generalizes zero-shot to multimodal reasoning on MATH-Vision.

Integrating Local and Global Entropy for Uncertainty Quantification in LLMs

Large language models hallucinate confidently, making uncertainty quantification (UQ) essential for reliable deployment. Existing methods rely predominantly on token-level signals, leaving the geometric structure of intermediate hidden states underused. In this paper, we take the geometric complexity of hidden-state matrices as a measure of the global uncertainty of LLMs, while treating token-level uncertainty estimation as a local metric. We show that hidden-state geometric entropy (global uncertainty) and token-level entropy (local uncertainty) are statistically near-orthogonal, capturing distinct failure regimes for reliability prediction. In particular, global geometry recovers the confident-but-wrong failure mode that local signals systematically miss. Building on this, we propose Global-Local Uncertainty (GLU), an unsupervised, single-pass score that fuses the two signals via a multiplicative gate. Across three model families and six benchmarks, GLU matches or outperforms all unsupervised baselines while requiring only a single forward pass and remaining length-normalized and architecture-agnostic.

TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition

Large language models (LLMs) have made remarkable progress in reasoning tasks, largely driven by post-training paradigms, especially reinforcement learning with verifiable rewards (RLVR). However, a critical bottleneck persists: RLVR fails on highly challenging zero-reward problems, where all sampled reasoning trajectories yield uniformly failed outcomes, providing no optimization signal to drive model improvement. Prior efforts to address this limitation, such as dense process supervision, partial reward assignment, or prefix-guided exploration, suffer from inherent task constraints or do not fully equip the policy model with the capabilities necessary to solve the original intractable problems. To address this, we propose TD-Grokking, a training-time decomposition framework for zero-reward problems. It recursively decomposes intractable root problems into self-contained, verifiable subproblems, forming hierarchical trees where solvable leaves provide non-zero rewards. Evaluations on mathematical and medical tasks show that TD-Grokking outperforms vanilla GRPO as well as all baseline approaches. Together with detailed analysis, these results confirm that training-time decomposition effectively converts zero-reward examples into usable training signals, enabling consistent performance gains. Our code and datasets are available at https://anonymous.4open.science/r/TD-Grokking-6567/.

Failure Modes of Deep Multi-Agent RL in Asynchronous Pricing: Reproducible Triggers, Trace Diagnostics, and a Partial Fix

We study two reproducible failure modes of deep multi-agent reinforcement learning in continuous-time pricing markets: (i) tacit cartel formation between competing DDPG agents, and (ii) actor--critic instability at high event rates. We instantiate both inside a single CT-MARL benchmark (Poisson-clocked price updates, observation latency $\delta$, interior-optimum logit demand), show that synchronous DDPG agents reliably trigger Failure Mode 1 with collusion index $\Delta = 0.69 \pm 0.11$, and quantify a partial microstructure fix: asynchrony alone cuts collusion by 48\% and adding latency drives it to a minimum of $\Delta = 0.28$. The fix has clearly documented costs: it is partial ($\Delta$ remains supra-Bertrand), it is non-monotone in $\delta$, and it does not survive Failure Mode 2, which emerges as DDPG critic divergence at $\lambda = 5$ and corrupts the phase-diagram cell at $(\lambda{=}5, \delta{=}1)$. We accompany the scalar collusion index with trajectory-level trace diagnostics that expose the within-episode signalling collapse and the post-shock non-recovery.

SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs

Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the memory wall: the full expert pool must remain resident to support token-dependent routing. Expert pruning is a direct remedy, but prior criteria typically score experts independently and overlook that MoE inference is inherently \emph{coalitional}, where outputs arise from routed top-$k$ expert combinations. We propose \textbf{SHAPE}, a task-driven pruning framework that explicitly models \emph{intra-layer} expert cooperation. SHAPE formulates routing traces on a small calibration set as an empirical cooperative game and assigns interaction-aware expert values via a Shapley-style attribution over observed top-$k$ coalitions, enabling the identification of experts that are essential for high-utility collaborations rather than merely frequent. To preserve MoE topology under a global pruning budget, SHAPE further introduces a \emph{quality-coverage} selection rule that retains, in each layer, the minimal expert subset covering an $\alpha$ fraction of non-negative Shapley mass, while using bisection to match a target keep rate. Experiments on three modern MoE backbones (Qwen3-30B-A3B, GPT-OSS-20B, and DeepSeek-V2-Lite) across diverse benchmarks show that SHAPE consistently improves robustness over global and layer-wise pruning variants, maintaining competitive accuracy under 20\% and 40\% expert pruning without additional training and delivering clear reductions in peak GPU memory footprint. The open-source code is available at https://github.com/Alizen-1009/Shapley-Moe.

SocraticPO: Policy Optimization via Interactive Guidance

Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization direction but rarely explain how a model should revise its mistaken reasoning, which can encourage shortcut learning and brittle policies. We propose \textbf{SocraticPO} (Socratic Policy Optimization), a policy-optimization framework that augments RL rollouts with Socratic-style natural-language guidance. During rollout, the student first answers independently; if the answer is incorrect, a teacher diagnoses the attempt and provides concise corrective guidance, after which the student continues under the expanded context. Crucially, this guidance is paired with reward decay: correct answers obtained after teacher intervention only receive decayed rewards, preventing the policy from treating teacher help as a free path to reward. Since SocraticPO only modifies the rollout process while leaving the standard expected-reward objective intact, it can be plugged into existing policy-gradient backends such as Reinforce++. Moreover, because the teacher provides only text-level guidance, SocraticPO can leverage stronger black-box teacher models without requiring access to logits or distribution matching. On undergraduate-level scientific reasoning benchmarks from SciKnowEval, SocraticPO improves over strong RL and self-distillation baselines. Ablations show that both targeted guidance and reward decay are necessary, with reward decay mitigating reliance on assisted correction.

PreAct-Bench: Benchmarking Predictive Monitoring in LLMs

Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective. While existing safety research has focused on detecting unethical behavior from complete trajectories, this paradigm is fundamentally retrospective: it identifies harm only after it has already occurred. In this work, we study a critical yet overlooked safety task, which we term Predictive Monitoring: given only a partial action trajectory, can a model infer whether it will culminate in an unethical action before the overt action is executed? To support this task, we present PreActBench, a benchmark of 1,000 paired ethical and unethical action trajectories spanning five domains. We evaluate a range of LLMs, safety guardrail models, and latent probing methods across varying fractions of the action trajectory using our Prefix Foresight F1 metric. Results show that while humans achieve promising performance, predictive monitoring remains challenging even for strong models, highlighting the need for future-oriented risk reasoning in LLM safety.

Representation Curriculum: Stagewise Training for Robust Ranking and Allocation

Ranking in digital marketplaces is a dynamic exposure-allocation mechanism: displayed items shape discovery trajectories and success events logged by the platform to update future allocation policies. Modern ranking systems rely heavily on exposure-confounded signals (e.g. popularity estimates, CTR/CVR aggregates, and ID-based representation), because they are highly predictive under stationary demand. Yet this predictive power can become a learning shortcut: early access to exposure-dependent belief signals steers optimization toward over-reliance on them and away from exposure-independent merit signals (e.g., content-based competitiveness and semantic affinity). Consequently, the learned policy tends to entrench incumbents and degrade cold-start generalization and robustness under distribution shift. We propose Representation Curriculum (RC), a training-time intervention that temporally stages feature utilization. RC foregrounds content-based merit signals initially, then introduces exposure-dependent belief signals while anchoring the content pathway near the learned merit representation, curbing shortcut reliance on historical signals and mitigating gradient starvation on content signals. We formalize RC independently of task and hypothesis class and provide ranking-specific instantiations. In a Gaussian linear ridge setting, we derive closed-form solutions and sufficient conditions under which RC strictly reduces population risk on a cold-start target distribution, with a quantified Pareto tradeoff against source performance. Experiments on public learning-to-rank and recommendation benchmarks, and randomized online experiments in a large-scale e-commerce search system, show that RC measurably shifts reliance from historical belief signals toward content-based merit signals and yields consistent gains on cold populations with a controlled trade-off in head performance.

Tractogram foundation model

Diffusion MRI (dMRI) tractography is the only noninvasive approach for mapping white-matter pathways in the living human brain. It represents each brain as a tractogram: a large, unordered set of three-dimensional streamlines that includes information about both local streamline geometry and whole-brain anatomical organization. This structure makes tractograms a natural but challenging target for representation learning. Existing methods treat streamline classification and subject-level prediction as separate problems: streamline classifiers focus on geometric patterns, whereas subject-level prediction often depends on hand-crafted features. As a result, current methods do not learn reusable representations that connect streamline anatomy with whole-brain inter-subject variation. Here we introduce TractFM, a tractogram foundation model that learns reusable representations directly from whole-brain streamline sets. TractFM combines a local streamline encoder with a permutation-equivariant tractogram encoder, allowing all streamlines from a subject to be contextualized jointly in a single forward pass. Pretraining on dense anatomical tract parcellation, i.e., assigning anatomical labels to individual streamlines, yields two complementary representations: contextualized streamline-level embeddings for tract parcellation and compact subject-level descriptors for downstream prediction of subject phenotypes. Across three tractography algorithms and five dMRI datasets, TractFM transfers to both streamline-level and subject-level tasks. Its frozen representations achieve accurate tract parcellation and predict age and sex across independent datasets. These results show that whole-brain geometric context, learned once, can generalize across tractography pipelines, datasets, and prediction tasks.

HMAF: A Hierarchical Multi-Slot GD-RTB Allocation Framework

In modern online advertising platforms, Guaranteed Delivery (GD) contracts coexist and bid with Real-Time Bidding (RTB) auctions. Recent approaches either decouple GD and RTB optimization or rely on heuristic priority rules, and thus fail to effectively balance short-term revenue maximization with long-term contract delivery under complex multi-slot delivery and impression constraints. To address these challenges, we propose HMAF (Hierarchical Multi-Slot Allocation Framework), a unified framework designed to optimize impression allocation in GD--RTB advertising platforms. HMAF employs the Plan--Calibrate--Execute paradigm as its core structure, and integrates offline constraint optimization with online decision-making, balancing offline GD resource planning, dynamically calibrating GD--RTB competitiveness, and making real-time listwise rank decisions across multi-slot environments. HMAF has been implemented in multiple marketing scenarios at Meituan, one of the world's largest online food delivery platforms, leading to a 3.72% increase in GD delivery rate and a 1.59% increase in total advertisement revenue.

When Attribution Patching Lies: Diagnosis and a Second-Order Correction

A central goal of mechanistic interpretability is to identify which internal components causally drive a language model's behavior. Because these importance estimates serve as the evidence for identifying circuits, systematic errors can lead to the misidentification of the underlying mechanisms. While activation patching provides a gold-standard causal metric, its computational cost is prohibitive at scale. Practitioners instead rely on attribution patching, a gradient-based, first-order approximation whose reliability remains poorly understood. In this work, we characterize the source of this unreliability, demonstrating that the dominant error stems from the non-linearities in the downstream network rather than local curvature at the patched component. This insight yields three practical tools: (i) a reliability score to detect untrustworthy estimates, (ii) error bounds quantifying potential attribution mis-specifications, and (iii) a Hessian-vector-product (HVP) correction that eliminates the leading-order error with only one additional backward pass. In evaluations across five model families (124M-9B parameters) and both random-token and naturalistic (name-swap) perturbations, HVP is the only second-order correction feasible at larger scale, where standard baselines like Integrated Gradients become computationally prohibitive. In comparative experiments, a multi-step HVP variant matches or exceeds the accuracy of Integrated Gradients at significantly lower compute, outperforming prior second-order baselines. These improvements lead to higher-fidelity circuit recovery on standard benchmarks and support a Screen-Flag-Fix workflow that targets computational effort only toward the components flagged as unreliable.

The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs

Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout. Biological neural connectomes, shaped by millions of years of evolution, may encode computational structure beyond what random reservoirs provide, yet whether that structure can be further enhanced by principled optimisation remains an open question. We address it by applying four gradient-free, bio-inspired optimisers (Particle Swarm Optimisation, Differential Evolution, Grey Wolf Optimiser, and Whale Optimisation Algorithm) to the edge weights of connectome-based echo-state networks across six species spanning six orders of magnitude in neural complexity: C. elegans (279 neurons), Drosophila (49 nodes), mouse (112), rat (73), macaque (29 regions, continuous FLNe synaptic strengths), and human structural MRI connectivity (83 parcels). Each connectome is evaluated on four canonical reservoir computing benchmarks: Memory Capacity (MC), Lorenz attractor prediction, NARMA-10 system identification, and Mackey-Glass chaotic time-series prediction. All four optimisers consistently outperform unoptimised biological baselines across every task and species when initialised from biological weights. WOA achieves the largest gains on every task: up to a 17x MC improvement (C. elegans: 1.39 to 23.91) and up to 89% NRMSE reduction (Mackey-Glass, human), corresponding to an average 214% improvement across all species and tasks. Crucially, random initialisation on the same topology reliably underperforms biology, establishing biological weight values as an essential inductive bias that topology alone cannot recover. These results position bio-inspired, biologically-initialised optimisation as a principled and broadly effective strategy for connectome reservoir computing across the animal kingdom.

A Sober Look at Agentic Misalignment in Automated Workflows

We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solve complex tasks, they often fail because agents act according to implicit proxy utilities that do not align with the intended human goals. We formally define these behaviors and analyze them within a Bayesian framework, showing that generic utilities naturally lead to posterior collapse of agents in automated workflows. To address this issue, we propose Agentic Evidence Attribution (AEA), a novel alignment paradigm that improves agent posteriors using context-specific evidence. AEA reasons over agent actions and provides structured evidence to correct misaligned behavior during collaboration. To better understand the role of evidence, we study two instantiations of AEA: self-reflection (internal evidence from the model) and weak-to-strong generalization (external evidence on the agentic trajectory). We show that a small evidence model effectively aligns the MAS by providing orthogonal failure attribution. Our results clarify the sources of agentic misalignment in automated workflows and show that evidence-based alignment can effectively improve agent collaboration and leads to reliable multi-agent systems built on automated workflows.

Parthenon Law: A Self-Evolving Legal-Agent Framework

As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes. We address each. A large-scale empirical study on Harvey LAB -- $12{,}510$ agent trajectories -- shows that even frontier agents remain far from completing matters in a single pass: per-criterion accuracy climbs with stronger models while strict matter completion stalls. We then introduce \textsc{Parthenon}, a self-evolving legal-agent framework that factors Model, Harness, Agent roles, legal Knowledge, deterministic Tools, and procedural Skills into auditable surfaces for source traceability, date and number grounding, deliverable compliance, and issue closure. Finally, an anti-leakage learning loop converts scored failures into task-agnostic edits to skills, tools, and knowledge, letting the system improve with experience -- as a firm refines its checklists and playbooks after each matter -- without touching model weights. Across our large-scale empirical analysis, \textsc{Parthenon} substantially improves the performance of state-of-the-art models and harnesses on legal-matter tasks.

A Geometric Account of Activation Steering through Angle-Norm Decomposition

Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior. More recently, spherical steering paradigms have been proposed to address limitations of additive interventions, often motivated by the assumption that hidden-state norm does not carry concept-relevant information. In this work, we revisit this assumption through a controlled empirical study designed to disentangle the roles of angular and radial components. We show that steering methods differ mainly in how they couple two geometric effects: changing a token's angular alignment with a concept direction and changing its hidden-state norm. Across seven language models, we find that concepts are represented primarily in angular structure, supporting the motivation for spherical methods, but that norm remains important for the stability and downstream effects of steering. Our results explain why interventions with similar concept-level effects can behave differently, and suggest that activation steering should be parameterized by interpretable angular and radial components of the intervention, rather than by a single additive coefficient that entangles these two effects.

Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care

Baichuan-M4 is Baichuan Intelligence's clinical-grade medical large model, designed for continuous care rather than single-turn medical question answering. It is built as a coordinated medical agent system around three pillars: Baichuan-Harness, a unified runtime that keeps reinforcement-learning training and real-world deployment consistent while enforcing action constraints, tool use, long-term patient memory, and multi-agent coordination; a core reasoning model trained with a continuous-care reinforcement-learning framework that integrates span-level reward modeling (SPAR++), reasoning-path compression, curriculum learning, and stabilized policy optimization; and a clinical tool layer for patient-memory management, authoritative evidence-based retrieval, and multimodal medical perception across documents, X-rays, and dermatology. On a cross-dimensional medical evaluation suite, Baichuan-M4 attains leading results in static medical knowledge and safety, dynamic OSCE-style consultation, long-context clinical memory, evidence-based retrieval, medical document OCR, and multimodal image understanding, while lowering the hallucination rate to 3.3%.

Representational Alignment with Chemical Induced Fit for Molecular Relational Learning

Molecular Relational Learning (MRL) is widely applied in natural sciences to predict relationships between molecular pairs by extracting structural features. The representational similarity between substructure pairs determines the functional compatibility of molecular binding sites. Nevertheless, aligning substructure representations by attention mechanisms lacks guidance from chemical knowledge, resulting in unstable model performance in chemical space (\textit{e.g.}, functional group, scaffold) shifted data. With theoretical justification, we propose the \textbf{Re}presentational \textbf{Align}ment with Chemical Induced \textbf{Fit} (ReAlignFit) to enhance the stability of MRL. ReAlignFit dynamically aligns substructure representation in MRL by introducing chemical Induced Fit-based inductive bias. In the induction process, we design the Bias Correction Function based on substructure edge reconstruction to align representations between substructure pairs by simulating chemical conformational changes (dynamic combination of substructures). ReAlignFit further integrates the Subgraph Information Bottleneck during fit process to refine and optimize substructure pairs exhibiting high chemical functional compatibility, leveraging them to generate molecular embeddings. Experimental results on nine datasets demonstrate that ReAlignFit outperforms state-of-the-art models in two tasks and significantly enhances model's stability in both rule-shifted and scaffold-shifted data distributions.

Improving Topic Modeling by Distilling Soft Labels from Language Models

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we introduce a novel topic model training framework by Distilling Soft Labels (DSL) from Language Models (LMs). To construct the contextually enriched reconstruction signals, we project the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary, and train the topic models to reconstruct the soft labels using the LM hidden states. This produces higher-quality topics that are more closely aligned with the underlying thematic structure of the corpus. Extensive experiments demonstrate that DSL achieves substantial improvements in topic coherence and assignment accuracy over existing baselines. Additionally, we also introduce a retrieval-based metric, which shows that our approach significantly outperforms existing methods in identifying semantically similar documents, highlighting its effectiveness for retrieval-oriented applications.

Updating the standard neuron model in artificial neural networks

From their inception in the 1950s, artificial neural networks (ANNs) started using the so-called point neuron model then prevalent in neuroscience, hoping that this analogy would allow for a better emulation of brain function. Over the years the neuroscience literature has shown that the point neuron model is too simplistic to properly represent many fundamental neural processes; however, the standard neuron model in ANNs still remains the same. Here we substitute it by a very recent model of cortical cells and demonstrate through theoretical analyses and experimental results how, simply by using a more realistic neural unit element without augmenting the number of parameters, the resulting ANNs offer a number of important advantages that include increases in expressivity, robustness and learning speed, and a reduction in memorization and the amount of training data needed.

CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation

Humans primarily rely on walking and running to traverse complex terrains. Similarly, humanoid robots should be able to smoothly transition between walking and running while maintaining natural and stable locomotion. However, unifying gait transition and multi-terrain adaptation within a single policy remains challenging due to gradient interference between tasks and the distribution shift caused by terrain variations. Although Mixture-of-Experts (MoE) architectures can mitigate multi-skill interference, direct joint training often fails to achieve clear expert specialization. To address these challenges, we propose CoRe-MoE, a two-stage reinforcement learning framework that decouples gait generation from terrain adaptation. In the first stage, a stable locomotion policy is learned to produce natural walking and running behaviors with smooth transitions. In the second stage, a terrain-aware MoE branch is introduced, and the gating network is trained with a contrastive objective to learn structured terrain representations and promote expert specialization. The final action is obtained through weighted fusion of the base gait policy and the terrain-aware branch, enabling the policy to preserve stable locomotion while adapting to complex terrains. Extensive simulation results demonstrate that the proposed method outperforms baseline approaches in terms of success rate, locomotion stability, and multi-terrain adaptability. Furthermore, zero-shot deployment on a Unitree G1 humanoid robot validates the effectiveness of our framework, achieving robust walking and running across stairs, slopes, steps, obstacles, and unstructured outdoor terrains while maintaining accurate foothold control and dynamic stability.