AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFrom Judgment Quality to Downstream Utility: Rethinking LLM-as-a-Judge for Open-Ended Tasks
arXiv:2609.37145v1 Announce Type: new Abstract: LLM-as-a-Judge is increasingly used to evaluate policy responses on open-ended tasks that lack ground-truth answers. Existing work often directly converts the resulting jud…
- arXiv cs.AIagentsWhen Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agents
arXiv:2609.37153v1 Announce Type: new Abstract: Tool-augmented data agents rely on tool outputs for analytical decisions. Yet successful execution can return plausible but incorrect evidence, requiring agents to decide w…
- arXiv cs.AIresearchFrom Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation
arXiv:2609.37157v2 Announce Type: replace Abstract: Learner simulation aims to reproduce how a particular learner behaves on new tasks. Although Large Language Models (LLMs) can generate increasingly fine-grained learnin…
- arXiv cs.AIagentsSimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priors
arXiv:2609.37172v2 Announce Type: replace Abstract: Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuristics. However, t…
- arXiv cs.AIagentsAbsorbed in Inertia: Activation Analysis for Computer-Use Agents
arXiv:2609.37176v1 Announce Type: new Abstract: Computer-use agents have become increasingly capable of executing tasks on live desktops through natural-language instructions, based on trajectories of screenshots, action…
- arXiv cs.AIresearchAccelerated surrogate dynamics for dynamical, stochastic system evolution
arXiv:2609.37184v1 Announce Type: new Abstract: Dynamic simulations are an entrenched way of gaining insight into the evolution of system dynamics. Their computational cost however is often prohibitively high, especially…
- arXiv cs.AIresearchV-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization
arXiv:2609.37198v1 Announce Type: new Abstract: Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few references while prese…
- arXiv cs.AIresearchLearning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning
arXiv:2609.37203v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for natural-language logical reasoning, where the final answer is easy to check but the proof behind it is not. In na…
- arXiv cs.AIresearchInformation Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis
arXiv:2609.37220v1 Announce Type: new Abstract: Exploring high-order correlations and long-range dependencies in brain networks holds significant value for both neuroscience research and clinical diagnosis. However, prev…
- arXiv cs.AIresearchOptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization
arXiv:2609.37221v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed to solve complex scientific and practical problems via iterative optimization. However, dynamically coordinating…
- arXiv cs.AIagentsAsking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive ag…
- arXiv cs.AIagentsFoundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
arXiv:2609.37267v1 Announce Type: new Abstract: Proactive LLM agents can turn idle compute into useful support before users ask. Yet even correct work can misread user context, impose review costs, or undermine trust. Th…
- arXiv cs.AIresearchTask-Relevant Null-Space Residuals for Non-Injective Neural Mappings
arXiv:2609.37272v1 Announce Type: new Abstract: Non-injective mappings in neural networks map distinct inputs to the same representation, thereby implicitly inducing equivalence relations in the input space. However, the…
- arXiv cs.AIresearchTransolver-$\sigma$: Joint Spectral-Physical Subspace Modeling for Neural PDE Solving
arXiv:2609.37279v1 Announce Type: new Abstract: Neural solvers offer efficient surrogates for numerical simulation of partial differential equations (PDEs). For time-dependent problems, strong one-step accuracy does not…
- arXiv cs.AIresearchAssayRouter: Historical Utility Priors for Frozen Molecular Predictor Routing
arXiv:2609.37285v1 Announce Type: new Abstract: Laboratories often face a new molecular assay with 16-64 labels and a bank of predictors whose training data and parameters are unavailable. The practical question is which…
- arXiv cs.AIresearchMetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller
arXiv:2609.37304v1 Announce Type: new Abstract: Large reasoning models improve performance on challenging problems by allocating additional computation before answering, but longer reasoning does not always lead to bette…
- arXiv cs.AIagentsReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents
arXiv:2609.37311v2 Announce Type: replace Abstract: Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative agents autonomously…
- arXiv cs.AIresearchMubric: Mutation Testing-Guided Rubric Generation for LLM Evaluation
arXiv:2609.37322v1 Announce Type: new Abstract: Rubric-based evaluation is widely used to assess LLM-based systems by decomposing response quality into task-specific scoring criteria. However, automatically generating ru…
- arXiv cs.AIresearchVISTA: Value-Informed Event Appraisal for Multimodal Emotion Conflict
arXiv:2609.37324v1 Announce Type: new Abstract: Conflicting emotional cues can be individually valid: a subdued voice may reflect a blocked goal while a smile satisfies a social obligation. Their interpretation depends o…
- arXiv cs.AIresearchSolving Without Stopping: On-Policy Distillation at Small Scale
arXiv:2609.37326v1 Announce Type: new Abstract: On-policy distillation, where a student learns from a stronger teacher's feedback on its own outputs, is a common way to pass reasoning to smaller models. We analyze what i…
- arXiv cs.AIagentsSeek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation
arXiv:2609.37353v1 Announce Type: new Abstract: Vision-Language Navigation (VLN) requires agents to continuously ground task progress from long-horizon instructions and partial egocentric observations. Existing VLM-based…
- arXiv cs.AIresearchTeaching LLMs to Generate Challenging MILP Instances via Solver Feedback
arXiv:2609.37356v1 Announce Type: new Abstract: Generating optimization instances that are both feasible and computationally challenging is crucial for benchmarking solvers and training learning-based optimization algori…
- arXiv cs.AIresearchPretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
arXiv:2609.37362v1 Announce Type: new Abstract: Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--efficiency trade-off of…
- arXiv cs.AIresearchBeyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation
arXiv:2609.37377v1 Announce Type: new Abstract: On-policy distillation (OPD) trains students using teacher feedback on their own sampled responses, yet how prompt choice shapes transfer across teacher-student pairs remai…
- arXiv cs.AIresearchDirect Experience World-Model Optimization: Learning the World Beyond Action Imitation
arXiv:2609.37398v1 Announce Type: new Abstract: World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning paradigms typically impr…
- arXiv cs.AIresearchRouting Should Pay for Itself: Sparse Supervision for Economical LLM Routing
arXiv:2609.37402v1 Announce Type: new Abstract: Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such a router, however,…
- arXiv cs.AIresearchDemistifying Data and Simulator Assumptions in Supervised Causal Discovery
arXiv:2609.37446v1 Announce Type: new Abstract: Supervised causal discovery learns to infer causal structure for a new dataset from training datasets paired with structural labels. These training pairs are typically simu…
- arXiv cs.AIagentsCommitment Hierarchies under Intent Revision: A Belief-Revision Account of Salvage in Tool-Use Agents
arXiv:2609.37453v1 Announce Type: new Abstract: When a user changes their mind partway through a task, an agent that has already split the task into sub-goals and paid for tool calls must decide, per cached sub-result, w…
- arXiv cs.AIagentsGoverning the Edge: Automating Commercial Property and Casualty Insurance Underwriting via a Hybrid Local-Cloud Multi-Agent Framework
arXiv:2609.37454v1 Announce Type: new Abstract: Underwriters in commercial Property and Casualty (P&C) insurance spend 30 to 40% of their time on administrative work rather than risk judgment, and a single submission tak…
- arXiv cs.AIagentsVeriWeave Govern: Evidence-Gated Deterministic Runtime Governance for Enterprise AI Agents
arXiv:2609.37457v1 Announce Type: new Abstract: Enterprise artificial-intelligence agents increasingly call tools, modify infrastructure, and process protected data, creating a need to separate action generation from act…
- arXiv cs.AIresearchCRASM-Gate: Deterministic-First Constraint- and Role-Aware Semantic Mapping with Selective Model Assistance Across Heterogeneous Industrial Standards
arXiv:2609.37458v1 Announce Type: new Abstract: Industrial standards often encode the same engineering concept through incompatible hierarchies, identifiers, roles, and structural constraints, so the nearest lexical or e…
- arXiv cs.AIresearchAuthority Before Utility: Non-Compensatory Control for Persistent LLM Memory
arXiv:2609.37474v1 Announce Type: new Abstract: Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion, or revocation makes…
- arXiv cs.AIagentsBoundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift
arXiv:2609.37475v1 Announce Type: new Abstract: Tool-using language-model agents can decide that an action is permissible and execute it only after security-relevant state has changed. We study this proposal-to-commit ga…
- arXiv cs.AIagentsSkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
arXiv:2609.37539v1 Announce Type: new Abstract: Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in recent agent paradi…
- arXiv cs.AIagentsHow Can Recommendation Feedback Evolve Agent Memory?
arXiv:2609.37544v2 Announce Type: replace Abstract: Content-generation agents continuously receive impressions, clicks, conversions, and negative feedback from recommendation systems, providing real-world outcome signals…
- arXiv cs.AIagentsRational Clarification by Assistive Agents via Value-of-Information Reasoning
arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the request --- risking m…
- arXiv cs.AIagentsFOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents
arXiv:2609.37590v1 Announce Type: new Abstract: LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation from attention dilutio…
- arXiv cs.AIresearchXU-RS: Explaining Credal Width in Random-Set Language Models
arXiv:2609.37594v1 Announce Type: new Abstract: Uncertainty estimates tell us how unsure a model is, but not why. Without knowing which parts of an input influences a model's uncertainty, we cannot tell whether that unce…
- arXiv cs.AIresearchFlattening the Connectome Spectrum: A Spectral Filter for FC Induces a Pretraining Target for fMRI Encoders
arXiv:2609.37642v1 Announce Type: new Abstract: Self-supervised pretraining reshaped prediction in language and vision, and brain foundation models (BFMs) inherited its promise. Representations learned from large unlabel…
- arXiv cs.AIresearchBeyond a single latent space: a dual-latent world model for long-horizon planning
arXiv:2609.37644v1 Announce Type: new Abstract: Latent world models often struggle with long-horizon planning despite accurate short-term predictions. Recursive rollouts accumulate errors, while distance concentration in…
- arXiv cs.AIagentsEnterpriseBench: Benchmarking LLM Agents on Enterprise-Level Strategic Reasoning and Decision-Making
arXiv:2609.37658v2 Announce Type: replace Abstract: LLM agents are increasingly expected to support enterprise workflows, where tasks often involve missing information, uncertainty, feedback, and long-term trade-offs. Ho…
- arXiv cs.AIresearchMeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators
arXiv:2609.37670v1 Announce Type: new Abstract: MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tuning: existing advant…
- arXiv cs.AIagentsKUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
arXiv:2609.37673v1 Announce Type: new Abstract: Experienced professionals know more than just facts and conclusions. They know which cues matter, why a judgment is reasonable, and which action to take. Routine work recor…
- arXiv cs.AIresearchLearning from Shared-Control Overrides: Context-Driven Acceleration Profile Prediction for Personalized Overtaking
arXiv:2609.37684v1 Announce Type: new Abstract: Adaptive Cruise Control (ACC) systems are typically calibrated for an average driver, often resulting in a mismatch between vehicle behavior and individual expectations dur…
- arXiv cs.AIagentsEngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
arXiv:2609.37686v2 Announce Type: replace Abstract: Autonomous agents have made rapid progress in general-purpose computer use, yet reliable automation of professional industrial engineering remains out of reach. Enginee…
- arXiv cs.AIresearchWISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
arXiv:2609.37687v2 Announce Type: replace Abstract: Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. Ho…
- arXiv cs.AIresearchLocating Answer-Correctness Signals in Frozen Large Language Models
arXiv:2609.37700v1 Announce Type: new Abstract: Language models expose internal signals that predict whether an answer is correct, readable from a single forward pass of a frozen model without additional generations. Yet…
- arXiv cs.AIresearchGenerative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics
arXiv:2609.37708v2 Announce Type: replace Abstract: Human social behaviour is not a collection of independent motions, but a jointly organised process in which group dynamics and individual variation continuously shape o…
- arXiv cs.AIresearchContext Language Models
arXiv:2609.37725v1 Announce Type: new Abstract: We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the mo…
- arXiv cs.AIresearchSpatiotemporal Hyperedges for EEG Seizure Detection and Prediction
arXiv:2609.37730v1 Announce Type: new Abstract: Seizure detection and prediction from EEG are clinically important but challenging because seizures are rare, temporally localized, and propagate as coordinated events acro…