AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRoute-Verify-Vote: Procedure-Conditioned Self-Consistency for Mixed-Domain Reasoning
arXiv:2610.08814v1 Announce Type: new Abstract: Compositional generalization remains challenging when language models must combine familiar reasoning operations in unfamiliar ways. The Scenario-Based Commonsense Reasonin…
- arXiv cs.AIagentsAn Empirical Study of Agent Skills' Downstream Utility
arXiv:2610.08875v2 Announce Type: replace Abstract: Agent Skills package procedural guidance and resources for reuse, but a relevant Skill does not necessarily improve task performance. Existing studies characterize Skil…
- arXiv cs.AIresearchHow Could AI Eliminate Humanity? A Failure-Mode Analysis of Civilizational Risk
arXiv:2610.08878v1 Announce Type: new Abstract: This article develops a failure-mode framework for analyzing how advanced artificial intelligence could contribute to human extinction, irreversible civilizational collapse…
- arXiv cs.AIagentsHumanize: Judgement Engineering for Agentic Coding
arXiv:2610.08900v2 Announce Type: replace Abstract: Agentic coding makes code generation cheap, but reliable completion remains difficult: the agent that writes the code is a weak judge of whether it is done. We present…
- arXiv cs.AIagentsSequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
arXiv:2610.08901v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents. In this work, we focus on parallel m…
- arXiv cs.AIagentsAgent Plasticity: Measuring Self-Improvement Through Experience
arXiv:2610.08902v1 Announce Type: new Abstract: AI agents increasingly operate in environments where they can diagnose failures and improve through experience, yet existing evaluations largely measure what an agent can d…
- arXiv cs.AIresearchAdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails
arXiv:2610.08923v1 Announce Type: new Abstract: Enterprise generative AI applications require robust safety mechanisms that can accommodate diverse risk postures, evolving policies, and varying latency constraints. Curre…
- arXiv cs.AIagentsCan AI Agents Make Open-Ended Scientific Discovery? Evidence from Station
arXiv:2610.08927v1 Announce Type: new Abstract: Recent AI systems have made rapid progress in scientific discovery when given well-defined metrics, but whether they can autonomously undertake open-ended scientific discov…
- arXiv cs.AIresearchHumanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
arXiv:2610.08966v2 Announce Type: replace Abstract: Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle…
- arXiv cs.AIresearchSocio-Foundation: A Model for Generalizable Individual Behavior Simulation via Hierarchical Capability Distillation
arXiv:2610.08967v1 Announce Type: new Abstract: Simulating individual behavior requires large language models (LLMs) to preserve persona traits while adapting to dynamic social contexts. However, general-purpose LLMs oft…
- arXiv cs.AIagentsVerify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents
arXiv:2610.08993v1 Announce Type: new Abstract: As large language models become more powerful, self-evolving agents are able to tackle challenging tasks including AI for machine learning (AI4ML). In AI4ML, while empirica…
- arXiv cs.AIagentsHow Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis
arXiv:2610.09000v1 Announce Type: new Abstract: As small language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as components of agentic systems, the integrity of loca…
- arXiv cs.AIagentsLearning to Report Unsafe Tasks in a Multi-Agent Game
arXiv:2610.09002v2 Announce Type: replace Abstract: When a team of agents shares a reward for completed tasks, reporting and stopping unsafe work reduces the team's reward. Random audits that penalize silence can make un…
- arXiv cs.AIresearchSigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering
arXiv:2610.09007v1 Announce Type: new Abstract: Detection engineers must translate threat reports, forensic observations, and hunt hypotheses into precise, testable rules. General-purpose large language models (LLMs) can…
- arXiv cs.AIagentsWhose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory
arXiv:2610.09008v1 Announce Type: new Abstract: Persistent memory allows an LLM agent to carry experience across conversations, but it also turns a local reasoning mistake into a durable one. During deliberation, an agen…
- arXiv cs.AIresearchEnabling Dynamic Computation in Looped LMs
arXiv:2610.09013v1 Announce Type: new Abstract: Looped LMs are parameter efficient and promise dynamic computation (saving memory and FLOPs on easy tokens). However, state-of-the-art open Looped LMs trained with this dyn…
- arXiv cs.AIresearchPAIR: Bridging Perception and Action in Vision-Language-Action Models
arXiv:2610.09016v1 Announce Type: new Abstract: Vision-language-action (VLA) models map visual observations and language instructions to continuous robot actions. This task requires a transition from representations that…
- arXiv cs.AIagentsNot Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System
arXiv:2610.09021v1 Announce Type: new Abstract: An agentic system issues several structurally different kinds of LLM calls. It routes intent, classifies actions, grounds language in a device registry, plans multi-agent p…
- arXiv cs.AIresearchBEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment
arXiv:2610.09026v1 Announce Type: new Abstract: We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavioral health settings suc…
- arXiv cs.AIagentsShared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network
arXiv:2610.09034v1 Announce Type: new Abstract: Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roadmap generation method…
- arXiv cs.AIagentsWhen the Governor Becomes the Disturbance: Control-Generated Disturbance and Cost-Aware Backoff in Governed Tool-Using Agents
arXiv:2610.09037v1 Announce Type: new Abstract: Supervisory governors can interfere with the tool-using agents they regulate. We study this possibility in a controlled file-recovery environment where increases in regulat…
- arXiv cs.AIresearchFrom High Recall to High Utility: Dataset-Adaptive Post-Processing of LLM-Generated Customer Intents
arXiv:2610.09039v1 Announce Type: new Abstract: Large language models can extract useful signals from heterogeneous enterprise data, but high-recall extraction often produces outputs that are duplicated, uneven in granul…
- arXiv cs.AIresearchJustice After Identity: Large Language Models and the View from Everywhere
arXiv:2610.09053v1 Announce Type: new Abstract: The search for a common view of justice and fairness has challenged human collective activity, as our diverging judgments are unavoidably shaped by the self-interests of so…
- arXiv cs.AIresearchEpistemic Uncertainty-Aware Defect Detection for Quality Control in Medical Device Manufacturing
arXiv:2610.09057v1 Announce Type: new Abstract: Objective: We investigate whether accounting for epistemic uncertainty can improve the reliability of automated defect detection in medical device manufacturing. Methods: W…
- arXiv cs.AIagentsRippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents
arXiv:2610.09088v1 Announce Type: new Abstract: Agent checkpoint systems decide what state is recovery-relevant, how to snapshot it, and whether rollback is admissible. None decides which of the safe boundaries they expo…
- arXiv cs.AIagentsConstraint Tree Exploration for Learning from Language Feedback
arXiv:2610.09107v1 Announce Type: new Abstract: Natural-language feedback in interactive learning often explains why an action failed by pointing to violated requirements. Misinterpreting this feedback can lead an agent…
- arXiv cs.AIagentsGeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks
arXiv:2610.09112v1 Announce Type: new Abstract: Before tool-using LLM agents are deployed in environmental and geospatial workflows, teams need evidence that an agent reliably selects the right operations against real AP…
- arXiv cs.AIagentsFrom Uncertainty to Action: Learning to Steer LLM Agents
arXiv:2610.09115v1 Announce Type: new Abstract: Steering an LLM agent means deciding whether to correct it, at which step, and with which mechanism. Uncertainty is often used to decide when to correct an agent, but wheth…
- arXiv cs.AIagentsWhich Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuation
arXiv:2610.09119v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) systems are becoming the interface to buildings, answering questions and controlling operations, but a building's readiness for them ha…
- arXiv cs.AIagentsCADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
arXiv:2610.09127v1 Announce Type: new Abstract: Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals…
- arXiv cs.AIresearchBreaking the Space Barrier and its Application to Language Model Inference
arXiv:2610.09139v1 Announce Type: new Abstract: Language models are more and more often asked for structured output: JSON that follows a schema, or a tool call with typed arguments. A small machine, an automaton, enforce…
- arXiv cs.AIresearchFinding Side-Effect Loopholes in Verifiable Rewards
arXiv:2610.09142v2 Announce Type: replace Abstract: In reinforcement learning with verifiable rewards, a benchmark's verifier supplies the reward. Reward-hacking audits mostly look for runs that pass without doing the ta…
- arXiv cs.AIresearchDIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies
arXiv:2610.09144v1 Announce Type: new Abstract: Vision-language-action (VLA) policies typically feed dense visual patch tokens into a language-action backbone, preserving scene context but offering no explicit mechanism…
- arXiv cs.AIresearchFrozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
arXiv:2610.09146v2 Announce Type: replace Abstract: Large language models (LLMs) and vision-language models (VLMs) are usually frozen after deployment, so they do not learn from the cases they solve. This is especially c…
- arXiv cs.AIagentsSpecGuard: Proving a Task Is Broken Before the Agent Cheats
arXiv:2610.09159v1 Announce Type: new Abstract: As autonomous coding agents get increasingly deployed, the risk that accidental or adversarially injected misspecifications in tasks lead to dangerous agent behavior is cri…
- arXiv cs.AIresearchTraining Language Models To Be Coherent Decision-Makers
arXiv:2610.09164v1 Announce Type: new Abstract: Reliable decision-making requires more than accurate prediction: a model must preserve its beliefs, apply the relevant utilities, and recognize when the information needed…
- arXiv cs.AIresearchFrom Probabilities to Decisions: Search and Multi-Teacher Distillation with Jev
arXiv:2610.09188v1 Announce Type: new Abstract: Probability-only models, which TypeSafe calls System One models, return calibrated probabilities for fixed choices in milliseconds and generate no text. We study one such m…
- arXiv cs.AIagentsBookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver
arXiv:2610.09193v1 Announce Type: new Abstract: MemoryAgentBench's Conflict Resolution split is read as measuring "selective forgetting". We execute the benchmark's own rule - the newest statement about a fact wins - as…
- arXiv cs.AIagentsFreeEvolve: Learning to Evolve Beyond Fixed Loops
arXiv:2610.09197v2 Announce Type: replace Abstract: Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is still designed by hand…
- arXiv cs.AIresearchFew Bits, One Law: Toward W2A4KV2
arXiv:2610.09202v1 Announce Type: new Abstract: Extreme low-bit LLM compression is most challenging when weights, activations, and KV caches are quantized together: their distributions differ, and quantization errors int…
- arXiv cs.AIresearchAGAR: a reinforcement learning substrate for LLM program evolution
arXiv:2610.09215v1 Announce Type: new Abstract: Given a task and an evaluator, a language model can rewrite a candidate program while a search loop decides which rewrites survive, offering a practical route to algorithm…
- arXiv cs.AIagentsRLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms
arXiv:2610.09218v1 Announce Type: new Abstract: LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self…
- arXiv cs.AIresearchCM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning
arXiv:2610.09219v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) treats all constraint violations equally: a $1 budget overshoot and a $1,000 overshoot induce the same training signal. It is also susc…
- arXiv cs.AIagentsTrajectory Abstraction for the Science of Language Agent Behavior
arXiv:2610.09237v1 Announce Type: new Abstract: Scientific studies of language agents need behavioral variables that support hypotheses across tasks and models. We formulate this research problem as learning and testing…
- arXiv cs.AIresearchThe Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules
arXiv:2610.09239v1 Announce Type: new Abstract: Self-improving LLM systems propose changes to themselves and keep those that score better on a small evaluation set. We treat this keep-if-better step as selection under me…
- arXiv cs.AIagentsWe Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents
arXiv:2610.09243v1 Announce Type: new Abstract: Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions such as scheduling, caching or isolation piecemeal from…
- arXiv cs.AIagentsRT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment
arXiv:2610.09294v1 Announce Type: new Abstract: Rapid progress in AI agents has brought growing attention to agent safety, with extensive evaluation focused on digital environments. As agents move into the physical world…
- arXiv cs.AIresearchThe AI Evaluation Ecosystem
arXiv:2610.09296v1 Announce Type: new Abstract: AI evaluation shapes the decisions of model providers, users, funders, and regulators. We argue that designing valid benchmarks requires contextualizing design choices in t…
- arXiv cs.AIagentsSearchWorld: Spatial Value-Grounded Imagination for UAV Object Search via World Models
arXiv:2610.09335v1 Announce Type: new Abstract: Autonomous unmanned aerial vehicle (UAV) object search involves a closed loop of perception, decision-making, and action under partial observability. Urban environments pos…
- arXiv cs.AIagentsRelevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA
arXiv:2610.09348v1 Announce Type: new Abstract: LLM agents that interact with a user across many sessions accumulate histories that exceed their context window, so they store past interactions in an external memory and a…