AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsNeos: Learning to Interleave Search and Visual Reasoning
arXiv:2610.17043v1 Announce Type: new Abstract: Recent multimodal deep search agents have advanced tool use and visual content retrieval, yet they still struggle to convert intermediate visual evidence into actionable gu…
- arXiv cs.AIresearchVL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval
arXiv:2610.17057v1 Announce Type: new Abstract: Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This leaves an important ga…
- arXiv cs.AIresearchPatientWM: Towards Generalizable Clinical World Models via Unified Patient States
arXiv:2610.17059v1 Announce Type: new Abstract: Clinical decisions depend on anticipating how a patient's condition will evolve as treatment is adjusted and new evidence becomes available. Existing medical world models c…
- arXiv cs.AIresearchSFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
arXiv:2610.17093v2 Announce Type: replace Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On the sparse co-a…
- arXiv cs.AIagentsWhen LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing
arXiv:2610.17118v1 Announce Type: new Abstract: Future AI-native networks are being designed to apply autonomous agents built on large language models (LLMs) in network management through intents. When intents from diffe…
- arXiv cs.AIagentsEvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research
arXiv:2610.17130v2 Announce Type: replace Abstract: Automated alpha factor discovery is critical for modern quantitative research. While large language models (LLMs) have increasingly been integrated into quantitative wo…
- arXiv cs.AIresearchThe Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express
arXiv:2610.17158v1 Announce Type: new Abstract: When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1--5 rating, 0--100 score, or comparison) is rarely justified or ablated. Holding the…
- arXiv cs.AIresearchLearning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors
arXiv:2610.17164v1 Announce Type: new Abstract: The relationship between odor chemistry and perception remains incompletely understood. Many existing studies focus on the perception of single molecules, whereas natural o…
- arXiv cs.AIresearchChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning
arXiv:2610.17183v1 Announce Type: new Abstract: Current chemistry benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an observed chemical effe…
- arXiv cs.AIresearchSize Generalization for Diffusion Routing Solvers
arXiv:2610.17192v1 Announce Type: new Abstract: Routing problems, like the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP), are NP-hard and slow to solve for large instances. Diffusion…
- arXiv cs.AIresearchReleasing the Inner Jev: A Simple Recipe for Open Decision Models
arXiv:2610.17205v1 Announce Type: new Abstract: LLM-based decision-making systems, also called System One models, have recently gained popularity, most notably through Jev (Almeida, 2026). Given a typed input state, a qu…
- arXiv cs.AIagentsAutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment
arXiv:2610.17206v1 Announce Type: new Abstract: We propose AutoMARS (Automatic Multi-Agent Risk Assessment), an agentic framework for automatic and scalable comparative risk assessment in supply chain networks. The frame…
- arXiv cs.AIresearchIsoVRBench: Video Reward Modeling Without Human Feedback
arXiv:2610.17234v1 Announce Type: new Abstract: Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignment, visual fidelity,…
- arXiv cs.AIresearchDoes a Governed Confidence Score Know When a Text-to-SQL Answer Is Right? An Exploratory Study on BIRD and a Pre-registered Confirmation on Spider
arXiv:2610.17256v2 Announce Type: replace Abstract: Conversational analytics lets people ask questions of records spread across many systems and get answers in plain language; it is useful only if each answer can be trus…
- arXiv cs.AIresearchRL Post-Training Diffusion Language Models Along Their Own Generation Paths
arXiv:2610.17266v1 Announce Type: new Abstract: Diffusion language models are a promising and more efficient alternative to autoregressive models. However, most RL post-training techniques are not easily adapted to these…
- arXiv cs.AIresearchReasoning for Propaganda Detection via Label-Guided CoT Optimisation
arXiv:2610.17271v1 Announce Type: new Abstract: Propaganda detection systems usually operate as black boxes, lacking explanations. To address this, we hypothesise that persuasive techniques contain definitional character…
- arXiv cs.AIagentsPhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction
arXiv:2610.17288v1 Announce Type: new Abstract: Building physical simulations from video requires coding agents to translate observations into executable models and refine them through tool use. We introduce PhysCodeGym,…
- arXiv cs.AIresearchTowards Resilience: Slice-Driven Orchestration of Mobile IoMT in 6G-Edge-Continuum
arXiv:2610.17296v1 Announce Type: new Abstract: Emerging healthcare services, such as real-time diagnostics, remote health monitoring and computer-assisted surgery, require stringent Quality of Service (QoS) guarantees w…
- arXiv cs.AIagentsThe Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow
arXiv:2610.17301v1 Announce Type: new Abstract: Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact decides whether an act…
- arXiv cs.AIagentsReliable Text-to-SQL in Resource-Constrained Settings with Small LLMs via Iterative Retry Workflows
arXiv:2610.17305v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently improved Text-to-SQL generation, but their computational cost can hinder deployment in resource-constrained settings. This paper…
- arXiv cs.AIagentsBeyond Successful Play: Diagnosing Opponent Modeling in Large Language Models
arXiv:2610.17310v1 Announce Type: new Abstract: Language-model agents are expected to adapt to others whose behavior changes through interaction. Yet adaptation may rely on learned behavioral patterns rather than theory…
- arXiv cs.AIagentsDo Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean
arXiv:2610.17331v1 Announce Type: new Abstract: General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. This makes it difficult…
- arXiv cs.AIagentsBudgeted KV-Cache Repair for Evolving Contexts
arXiv:2610.17338v1 Announce Type: new Abstract: Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation. Later key-value (K…
- arXiv cs.AIagentsWhen Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions
arXiv:2610.17365v1 Announce Type: new Abstract: As LLM agents take on more autonomous roles, they may interact with multiple clients and counterparties whose goals and incentives conflict. If an agent maintains shared in…
- arXiv cs.AIresearchWhat Makes a Latent Space Shared? Direct and Recoverable Compatibility in Motion VAEs
arXiv:2610.17376v1 Announce Type: new Abstract: A shared latent space is often assumed to make representations from different schemas directly interchangeable, yet sharing parameters, dimensionality, or a prior does not…
- arXiv cs.AIagentsGet In, Decide, Prove: A Merchant-Side Readiness Benchmark for Agentic Commerce
arXiv:2610.17378v1 Announce Type: new Abstract: AI agents now browse and buy on people's behalf, and benchmarks measure how well the agents perform. Far less is known about the other side of the transaction: whether a me…
- arXiv cs.AIresearchEPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design
arXiv:2610.17379v1 Announce Type: new Abstract: LLM-based automated heuristic design (AHD) discovers heuristics for combinatorial optimization problems (COPs), where an LLM generates candidates in an evolutionary search.…
- arXiv cs.AIresearchLearning to Play: Reinforcement Learning and Games
arXiv:2610.17391v1 Announce Type: new Abstract: Amazing breakthroughs in reinforcement learning have taken place. Computers teach themselves to play Chess and Go and beat world champions. There is talk about expanding ap…
- arXiv cs.AIresearchGeneralizable field of view extension for diffusion MRI via conditional flow matching
arXiv:2610.17401v1 Announce Type: new Abstract: Incomplete field-of-view (FOV) diffusion MRI (dMRI) acquisitions compromise whole-brain white matter analysis by excluding brain regions from tractography and connectivity…
- arXiv cs.AIagentsAgency as a New Organizing Abstraction for Computer Science
arXiv:2610.17410v1 Announce Type: new Abstract: Advances in large-scale machine learning have enabled agentic AI systems: persistent, autonomous computational entities that pursue goals, initiate actions, and interact wi…
- arXiv cs.AIagentsSchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding
arXiv:2610.17436v1 Announce Type: new Abstract: Large language models (LLMs) on mobile devices can act as agents that call external software tools to complete complex tasks, but the major challenge of supporting on-devic…
- arXiv cs.AIagentsLarge Language Models Extend Known Research But Do Not Create New Research Directions
arXiv:2610.17439v1 Announce Type: new Abstract: The success of autonomous research systems relies on the quality of the scientific hypotheses they generate. Recent studies report that human reviewers often rate LLM-gener…
- arXiv cs.AIresearchAn FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification
arXiv:2610.17463v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are promising for energy-efficient spatiotemporal pattern recognition at the edge, but efficient deployment and on-device adaptation require…
- arXiv cs.AIresearchREA: From Correct LLM Judgments to Safe Decision Delivery
arXiv:2610.17473v1 Announce Type: new Abstract: Generative safety guards must classify requests correctly and return outputs that applications can parse. Reasoning guards can improve classification accuracy while produci…
- arXiv cs.AIresearchTacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency
arXiv:2610.17540v1 Announce Type: new Abstract: Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for a…
- arXiv cs.AIresearchReference Wording Shapes Retrieval of Robot Task Instructions
arXiv:2610.17549v1 Announce Type: new Abstract: Identifying a robot task from a short instruction is sensitive to which descriptions are available for retrieval. We investigate this effect in the natural-language instruc…
- arXiv cs.AIresearchRAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control
arXiv:2610.17584v1 Announce Type: new Abstract: Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while controlled action--resp…
- arXiv cs.AIagentsVerifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks
arXiv:2610.17609v1 Announce Type: new Abstract: Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how it handles later task…
- arXiv cs.AIresearchOpenDepth: Repurposing Image Editing Priors for Robust Open-World Monocular Depth Estimation
arXiv:2610.17610v2 Announce Type: replace Abstract: Recently, the integration of generative priors has revolutionized Monocular Depth Estimation (MDE), achieving state-of-the-art (SOTA) performance with remarkably high d…
- arXiv cs.AIagentsMAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification
arXiv:2610.17613v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) can solve complex problems beyond the reach of a single agent by decomposing tasks and coordinating complementary…
- arXiv cs.AIagentsExecutable Prefix Values for Locating Agent Failures
arXiv:2610.17633v1 Announce Type: new Abstract: Work on debugging LLM agents treats the "first mistake" marked by a human or LLM judge as ground truth for where a trajectory failed. We ask whether such labels point at ca…
- arXiv cs.AIresearchBeyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)
arXiv:2610.17641v1 Announce Type: new Abstract: Bias scores in language-model evaluations often conflate what a model prefers with whether it answers at all. We identify this confound in \textsc{BBQ}, whose ambiguous sco…
- arXiv cs.AIagentsWhen Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned?
arXiv:2610.17643v1 Announce Type: new Abstract: An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmation, call one or sev…
- arXiv cs.AIagentsCan Agents Truly Forget? Explore Machine Unlearning for LLM Agents
arXiv:2610.17659v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong capabilities in interactive problem solving, tool use, and long-horizon task execution. However, they may also acquire s…
- arXiv cs.AIresearchRoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
arXiv:2610.17665v3 Announce Type: replace Abstract: Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of…
- arXiv cs.AIagentsCowork-Gym: Synthesizing Interactive Work Environments at Scale
arXiv:2610.17670v1 Announce Type: new Abstract: Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires m…
- arXiv cs.AIresearchEncounter-Driven City-Scale Human Mobility Generation with Large Language Models
arXiv:2610.17672v2 Announce Type: replace Abstract: Large language models (LLMs) have shown strong potential for human mobility generation by modeling individual routines, activities, and mobility preferences. However, e…
- arXiv cs.AIresearchStable Token-level Scheduling for Serverless LLM Inference
arXiv:2610.17689v1 Announce Type: new Abstract: Serverless inference is emerging as an efficient deployment model for Large Language Models (LLMs) due to its ability to elastically scale resources, improve GPU utilizatio…
- arXiv cs.AIresearchMedEvo: Medical Reasoning Evolution through Knowledge Navigation
arXiv:2610.17690v2 Announce Type: replace Abstract: Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed trajectories, while ge…
- arXiv cs.AIresearchUnderstanding Gene Expression-to-Image Learning: Spatial Structure and Information Fidelity
arXiv:2610.17699v1 Announce Type: new Abstract: Single-cell RNA sequencing (scRNA-seq) enables cell-level analysis of biological heterogeneity, but learning effective representations from high-dimensional, unordered gene…