AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsSWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents
arXiv:2609.32631v1 Announce Type: new Abstract: Long-horizon software engineering (SWE) agents trained with reinforcement learning with verifiable rewards (RLVR) typically receive only terminal outcome supervision, makin…
- arXiv cs.AIresearchCan Open-Weight Large Language Models (LLMs) Simulate Human Survey Populations? A Cross-Instrument Calibration Study
arXiv:2609.32638v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate synthetic survey respondents and digital twins of real people, but whether their output preserves real human…
- arXiv cs.AIagentsBusiness Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery
arXiv:2609.32643v1 Announce Type: new Abstract: Detecting compromised business ad accounts is a challenge in digital advertising, as attackers exploit hijacked accounts to launch fraudulent campaigns. Large Language Mode…
- arXiv cs.AIagentsFrom Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving
arXiv:2609.32645v1 Announce Type: new Abstract: Autonomous-driving question answering requires reasoning over structured scene information, yet existing vision-language approaches largely delegate heterogeneous reasoning…
- arXiv cs.AIresearchPrediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions
arXiv:2609.32652v3 Announce Type: replace Abstract: Soft state representations assign states nonnegative class weights that sum to one, but agreement with reference labels does not guarantee accurate prediction of the ne…
- arXiv cs.AIresearchMixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off
arXiv:2609.32656v1 Announce Type: new Abstract: Multivariate Time Series Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about the future of another.…
- arXiv cs.AIresearchWorld Models with Predictable Long-Horizon Marginals
arXiv:2609.32657v1 Announce Type: new Abstract: Accurate one-step predictions do not ensure that a world model's rollouts retain the data distribution. We make the model's decoded stationary law explicit by learning a de…
- arXiv cs.AIagentsContract Memory Compiler: Resolve, Then Traverse
arXiv:2609.32658v1 Announce Type: new Abstract: External memory lets language-model agents answer questions about histories too long for the answer model's context window. Updates create a harder problem than retrieving…
- arXiv cs.AIresearchLearning from a Thoughtful Teacher: Adaptive On-Policy Self-Distillation for Mathematical Reasoning
arXiv:2609.32667v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a question-only student with token-level feedback from a teacher given training-only privileged information (PI). OPSD therefore p…
- arXiv cs.AIresearchRefinement Symmetry in Multimodal Transformers
arXiv:2609.32669v1 Announce Type: new Abstract: Attention weights depend on token counts, which change with the representation of a signal. We study refinement symmetry: splitting a representation while preserving conten…
- arXiv cs.AIresearchWhat Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation
arXiv:2609.32670v1 Announce Type: new Abstract: When a language model explains an answer it has already given, does it reuse the computation that produced the answer or reconstruct a story from the answer alone? Attribut…
- arXiv cs.AIresearchExpected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers
arXiv:2609.32674v1 Announce Type: new Abstract: On-policy reasoning models can learn from task rewards or teacher signals, but these sources differ in form and can favor conflicting updates, leaving unclear which should…
- arXiv cs.AIagentsWhen Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds
arXiv:2609.32677v1 Announce Type: new Abstract: Self-improving agents increasingly rely on proxy verifiers to choose policy updates, yet deployment can change the world in which those updates are evaluated. An update tha…
- arXiv cs.AIresearchPINNMorph: Evolving Online Adaptation Policies for Physics-Informed Neural Networks
arXiv:2609.32685v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) provide a learning-based framework for solving partial differential equations (PDEs), yet their training behavior can change substa…
- arXiv cs.AIagentsDude, Where's My State? Execution Information Requirements for Stateful Agents
arXiv:2609.32687v2 Announce Type: replace Abstract: Long-running agents must preserve information that later steps depend on. We introduce the Execution Information Requirement (EIR), a lower bound on the information tha…
- arXiv cs.AIagentsWorld Agent: Can Language Models Keep a World Running?
arXiv:2609.32692v1 Announce Type: new Abstract: World models are moving from generating realistic frames to generating playable worlds, yet whether a delivered world can keep running is not tested anywhere. Existing eval…
- arXiv cs.AIagentsIGSD: Environment-Verified Hindsight Self-Distillation for Search Agents
arXiv:2609.32694v1 Announce Type: new Abstract: On-policy self-distillation densifies agent training without external teachers: a policy conditioned on privileged hindsight provides step-level guidance for its own unpriv…
- arXiv cs.AIresearchFlat-Consensus Diffusion for Robust Data Reshaping under Noisy Evaluator
arXiv:2609.32696v1 Announce Type: new Abstract: Data shape determines how features are structured, how patterns are separated, and how distributions cover the underlying domain. Poor data shape can make models learn nois…
- arXiv cs.AIagentsCAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration
arXiv:2609.32700v1 Announce Type: new Abstract: LLM-powered autonomous systems have demonstrated promising capabilities in mathematical reasoning, engineering, and cybersecurity. Yet how to organize these systems for eff…
- arXiv cs.AIagentsDespite Instructions: Frontier Agents Improvise Covert Channels at Test Time
arXiv:2609.32701v2 Announce Type: replace Abstract: In security-sensitive applications, language-model agents are often required to coordinate without disclosing confidential information. Yet repeated interactions may al…
- arXiv cs.AIresearchCoWindow Attention: Full Causal Coverage Is a Collective Property
arXiv:2609.32704v1 Announce Type: new Abstract: FullAttn repeatedly exposes the complete causal history to every attention head, creating substantial redundant computation and memory traffic even with IO-efficient dense…
- arXiv cs.AIresearchMassAlloc Attention: Let Attention Allocate Its Own Compute
arXiv:2609.32712v1 Announce Type: new Abstract: FullAttn often assigns negligible normalized mass to much of the causal score space, yet dense kernels execute the complete post-score path after forming each QK tile. We i…
- arXiv cs.AIagentsSkillVine: Agent Skill Evolution via Branching Exploration
arXiv:2609.32731v1 Announce Type: new Abstract: Agent skills encapsulate reusable procedural knowledge that enables LLM agents to perform tasks, and they can be improved automatically using trajectories from interactions…
- arXiv cs.AIresearchRetrospective Distillation Attribution via Normalized Response Similarity
arXiv:2609.32749v1 Announce Type: new Abstract: Model distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising questions of model proven…
- arXiv cs.AIagentsCUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning
arXiv:2609.32750v1 Announce Type: new Abstract: Reinforcement learning enables computer-use agents to improve through interaction with real software environments, including websites and desktop applications. However, con…
- arXiv cs.AIresearchAction Shaping: Policies Absorb What They Can Express
arXiv:2609.32752v2 Announce Type: replace Abstract: Reward shaping has a theorem: a potential-based term can be removed without changing the optimal policy. The same practice on the action channel, an offset added in tra…
- arXiv cs.AIagentsAdaptive Consistency Graph for Long-Horizon Agents
arXiv:2609.32754v2 Announce Type: replace Abstract: Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequences of dependent a…
- arXiv cs.AIresearchReadout is not Recovery: Dissociating Coordinate Emission from Visual-Corruption Repair in Vision-Language Models
arXiv:2609.32757v1 Announce Type: new Abstract: VLM bounding-box localization is both language generation and spatial commitment. Parseable fields such as bbox_2d make localization easy to score, but dimensions that emit…
- arXiv cs.AIresearchMandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them
arXiv:2609.32763v1 Announce Type: new Abstract: Historical photographs and other canonical images can now be edited seamlessly with a single instruction, often leaving no reliable pixel-level trace. In such cases, the on…
- arXiv cs.AIresearchForecasting Intraday USD/CAD Exchange Rate with News-Derived Monetary-Policy Signals
arXiv:2609.32773v1 Announce Type: new Abstract: Monetary-policy announcements and central-bank communications play a central role in foreign exchange markets, yet their qualitative, unstructured form makes their forecast…
- arXiv cs.AIagentsAgentic Network Traffic Monitoring
arXiv:2609.32778v1 Announce Type: new Abstract: As the use of agentic artificial intelligence increases in nearly every industry, there exists a widening attack surface. It is necessary to monitor agents to ensure that a…
- arXiv cs.AIresearchLearning response-aware patient dynamics for respiratory support
arXiv:2609.32782v3 Announce Type: replace Abstract: Respiratory support can shape the short-term physiological trajectory of critically ill patients, but patients receiving the same intervention may follow different phys…
- arXiv cs.AIagentsCLAIRE: A Schema-Grounded Hybrid Workflow for Healthcare Administrative Form Completion
arXiv:2609.32787v1 Announce Type: new Abstract: Healthcare administrative staff transfer structured information from electronic health records, referrals, claims systems, provider rosters, and work queues into dynamic fo…
- arXiv cs.AIresearch$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training
arXiv:2609.32791v2 Announce Type: replace Abstract: Reinforcement mid-training lets language models learn internal thoughts from unlabeled text, but efficient token-level credit assignment remains challenging. Existing g…
- arXiv cs.AIagentsAgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks
arXiv:2609.32795v1 Announce Type: new Abstract: Large language model (LLM) agents assist users with everyday tasks that can be completed in many reasonable ways. Even when their answers are useful, how agents carry out t…
- arXiv cs.AIagentsPlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents
arXiv:2609.32801v1 Announce Type: new Abstract: Embodied task planners may produce multi-step plans whose subtask dependencies and interactions with the environment create physical risks during execution. Yet existing sa…
- arXiv cs.AIagentsRe-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault
arXiv:2609.32802v1 Announce Type: new Abstract: One variable sets what an upstream fault costs a staged pipeline of language-model agents: re-derivability, how much of what a stage needs it can rebuild from the original…
- arXiv cs.AIagentsNutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
arXiv:2609.32803v1 Announce Type: new Abstract: Generative and Agentic IoT systems offer a promising foundation for digital healthcare applications that combine sensing, personalized reasoning, and autonomous interaction…
- arXiv cs.AIagentsDecision-Sufficient State Representations: Measuring and Reducing Write-Time Regret
arXiv:2609.32805v2 Announce Type: replace Abstract: Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line of work therefore h…
- arXiv cs.AIresearchBeyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs
arXiv:2609.32807v2 Announce Type: replace Abstract: Clinical LLM evaluation often emphasizes answer accuracy; however, accuracy alone does not test counterfactual consistency or demographic robustness. We evaluated six L…
- arXiv cs.AIresearchOverwhelmed by Choice: Studying LLM Decision Making at Scale
arXiv:2609.32809v1 Announce Type: new Abstract: Multiple-choice and candidate-selection evaluations are widely used to assess LLM reasoning and decision-making, yet most benchmarks contain relatively small candidate sets…
- arXiv cs.AIresearchRight Answer, Wrong Reason: Accuracy, Consistency, and Consensus Are Misleading Indicators of LLM Faithfulness in Clinical Decision Support
arXiv:2609.32817v2 Announce Type: replace Abstract: Clinical Large Language Models (LLMs) achieve strong medical-exam accuracy; however, a correct answer does not guarantee that the explanation names the concepts that ac…
- arXiv cs.AIresearchWhen Can First-Order Models of Fine-Tuning Bound Forgetting?
arXiv:2609.32818v1 Announce Type: new Abstract: Fine-tuning a language model on new data can make it forget facts that it should keep. We ask whether measurements taken at the start of a fine-tuning run can bound, for ea…
- arXiv cs.AIresearchRank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic
arXiv:2609.32819v1 Announce Type: new Abstract: Raising the update-to-data (UTD) ratio breaks off-policy critics in two ways grouped as "plasticity loss": collapsing representations and growing value magnitude $|Q|$. We…
- arXiv cs.AIresearchRouting Drift Alone Does Not Diagnose Failure in Merged MoE LLMs
arXiv:2609.32821v1 Announce Type: new Abstract: Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mixture-of-Experts (MoE)…
- arXiv cs.AIresearchThe Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces
arXiv:2609.32825v1 Announce Type: new Abstract: A four-stage LLM pipeline gives up as much as 40.5 accuracy points at its own interfaces (gemma-3-12B on MATH-500, Holm-corrected p = 1.66e-19; the largest tax in the prima…
- arXiv cs.AIagentsImproving LLM Collaboration via Multi-Agent Preference Learning
arXiv:2609.32827v1 Announce Type: new Abstract: Several works have explored multi-agent reinforcement learning (MARL) in LLM collaboration. However, constructing reliable rewards is difficult in practice, as complete and…
- arXiv cs.AIagentsFinancialAuditBench: Benchmark Construction under Differential Privacy Using Real-World Priors
arXiv:2609.32835v1 Announce Type: new Abstract: As AI agents are becoming widely adopted in the financial services industry, careful measurement is essential to understand where they can be reliably deployed and where ov…
- arXiv cs.AIagentsCounterfactual Self-Evolving Agents for Evidence-Grounded Reasoning
arXiv:2609.32870v1 Announce Type: new Abstract: Self-play proposer--solver methods improve reasoning by generating tasks and learning from verified solutions. However, for evidence-identifiable tasks, where case-specific…
- arXiv cs.AIresearchCan LLMs Predict the Future? A Brier Score Analysis of Prediction Markets
arXiv:2609.32885v1 Announce Type: new Abstract: We study whether model upgrades improve probability estimates for prediction-market questions. Our Resolved Market Forecasting (RMF) benchmark contains 3,000 resolved binar…