AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsDynamic Conflict Clustering with Lightweight Learning and Strategic Repair for Distributed Constraint Satisfaction
arXiv:2610.15658v1 Announce Type: cross Abstract: Distributed Constraint Satisfaction Problems (DCSPs) model distributed decision-making in multi-agent systems, where agents assign values to local variables while satisfy…
- arXiv cs.AIagentsSkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification
arXiv:2610.15725v2 Announce Type: replace-cross Abstract: Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to unauthorized cop…
- arXiv cs.AIagentsA Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
arXiv:2610.15765v1 Announce Type: cross Abstract: Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designed for human end user…
- arXiv cs.AIagentsSurgiCLAW: An Interpretable Atomic-Skill Agent for Precision Robotic Micromanipulation
arXiv:2610.15766v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) and vision--language--action models have provided robots with new capabilities for long-horizon task understanding and pla…
- arXiv cs.AIagentsLLM Value Functions for Credit Assignment in Agentic RL
arXiv:2610.15840v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assigning credit to individ…
- arXiv cs.AIagentsScalable Weak-to-Strong Verifier Hardening for Agent Environments
arXiv:2610.15924v1 Announce Type: cross Abstract: Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. Verifiers can be attac…
- arXiv cs.AIagentsEmbedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs
arXiv:2610.15976v1 Announce Type: cross Abstract: This paper investigates a new role of randomness in stochastic policies--as a medium for embedding and communicating information. Specifically, we consider an agent inter…
- arXiv cs.AIagentsOf Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents
arXiv:2610.16027v1 Announce Type: cross Abstract: Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed error may be inherited…
- arXiv cs.AIagentsWhen Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems
arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to one authorized agent…
- arXiv cs.AIagentsWhen Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark
arXiv:2610.16067v2 Announce Type: replace-cross Abstract: Agent evaluation harnesses are software: they run a test suite, drive a test input generator, and decide outcomes with a test oracle. We audit them for defects a…
- arXiv cs.AIagentsDream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems
arXiv:2610.16071v1 Announce Type: cross Abstract: Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes. These auditors typically…
- arXiv cs.AIagentsPID-Gated Continual Prompt Adaptation Under Noisy Feedback
arXiv:2610.16129v1 Announce Type: cross Abstract: Deploying LLM agents in non-stationary environments requires continually revising their instructions as the task drifts, yet rewriting after every reported mistake can tu…
- arXiv cs.AIagentsLook Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation
arXiv:2610.16224v1 Announce Type: cross Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challenging. Existing agenti…
- arXiv cs.AIagentsAutoNovo: Agentic Program Search Discovers Transferable Nucleic Acid Design Algorithms
arXiv:2610.16232v1 Announce Type: cross Abstract: In-silico optimization of nucleic acids relies on predictive oracles that imperfectly capture biological function, so sequences optimized against one model may exploit mo…
- arXiv cs.AIagentsAvoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation
arXiv:2610.16251v1 Announce Type: cross Abstract: Deep-search agents are commonly trained by distilling tool-use trajectories from stronger teacher models. However, structurally complex questions may remain relatively ea…
- arXiv cs.AIagentsSLDBench v2: Active Scaling Law Discovery
arXiv:2610.16297v2 Announce Type: replace-cross Abstract: Scaling laws predict large-model performance from small experiments, but finding a reliable law itself requires costly experiments. SLDBench tests whether languag…
- arXiv cs.AIagentsDrafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems
arXiv:2610.16491v1 Announce Type: cross Abstract: Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget. A narrow search can miss useful sequences of edits,…
- arXiv cs.AIagentsFrom Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations
arXiv:2610.16498v1 Announce Type: cross Abstract: Generative Social Simulation (GSS) leverages Large Language Models (LLMs) to create sophisticated personas that define agents with demographics, emotions, and political o…
- arXiv cs.AIagentsAudit Before You Distill: A Controlled Workflow for Reasoning Transfer into Compact Medical Language Models
arXiv:2610.16713v1 Announce Type: cross Abstract: Teacher rationales can help a smaller model answer health professions questions, but they can also reinforce errors. We examined when they help and how this evidence can…
- arXiv cs.AIagentsPrivacyGuard: Source-Linked Sanitization and Locally Resolvable PII References for Cloud GUI Agents
arXiv:2610.16778v1 Announce Type: cross Abstract: Cloud graphical user interface (GUI) agents send instructions and screenshots to remote planners, exposing personally identifiable information (PII). Existing placeholder…
- arXiv cs.AIagentsDavinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments
arXiv:2610.16867v1 Announce Type: cross Abstract: Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved. Scaling either…
- arXiv cs.AIagentsAUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding
arXiv:2610.16985v1 Announce Type: cross Abstract: Vision-language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel in long-tail scenario…
- arXiv cs.AIagentsCWE-bench: Refocusing Agentic Security from Exploitation to Defense
arXiv:2610.17020v1 Announce Type: cross Abstract: Cybersecurity evaluations of AI agents have focused largely on offense, yet a working exploit does not show that an agent can make software safe. An attacker needs to exp…
- arXiv cs.AIagentsInteractive Navigation Beyond Reachability: Benchmark and Agentic Framework
arXiv:2610.17089v1 Announce Type: cross Abstract: Existing embodied navigation tasks commonly assume that traversability and object states remain fixed during an episode. Yet reaching a goal may require opening a door to…
- arXiv cs.AIagentsWho is the 'I' in AI? Establishing Decentralized Identity and Accountability for Autonomous Agents
arXiv:2610.17126v1 Announce Type: cross Abstract: The rapid proliferation of autonomous AI agents in decentralized ecosystems challenges existing identity paradigms. While human identity is traditionally anchored in biol…
- arXiv cs.AIagentsDeleting Code Without Losing Knowledge: Regenerative Software for Python Libraries
arXiv:2610.17197v1 Announce Type: cross Abstract: In the age of "Software 3.0", when a complete program can be rewritten in minutes by an agent, the traditional approach of relying on code as the sole source of truth bec…
- arXiv cs.AIagentsWhy Agentic Workflows Fail: A Taxonomy Derived from Literature and Empirical Data
arXiv:2610.17418v1 Announce Type: cross Abstract: Agentic workflows combine large language models with planning, memory, tools, execution environments, and iterative feedback. Their failures are difficult to diagnose bec…
- arXiv cs.AIagentsClearNav: Perception-Aligned Quadrotor Flight Using Differential-Physics
arXiv:2610.17419v1 Announce Type: cross Abstract: Autonomous quadrotor flight in cluttered environment is an key capability for tasks like inspection and search. Navigation policies trained in simulation and transferred…
- arXiv cs.AIagentsThe belief-action gap in language model agents
arXiv:2610.17444v1 Announce Type: cross Abstract: Language model (LM) agents can fail for different reasons, requiring different explanations and interventions. We study how state beliefs, action values, and action prefe…
- arXiv cs.AIagentsFoundation Models for Event Prediction Across Heterogeneous Event Logs
arXiv:2610.17503v1 Announce Type: cross Abstract: Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational systems. Yet event logs…
- arXiv cs.AIagentsMany Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
arXiv:2610.17544v2 Announce Type: replace-cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves re…
- arXiv cs.AIagentsDeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
arXiv:2610.17666v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps. Within-group step co…
- arXiv cs.AIagentsLatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents
arXiv:2610.17685v1 Announce Type: cross Abstract: Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local risks, overlooking f…
- arXiv cs.AIagentsTSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
arXiv:2610.17726v1 Announce Type: cross Abstract: Large language model (LLM) agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning--acquiring new skills often degrade…
- arXiv cs.AIagentsSkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
arXiv:2610.17727v2 Announce Type: replace-cross Abstract: Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively si…
- arXiv cs.AIagentsAuditing Failure Attribution: Label Predictability and Judge Behavior
arXiv:2610.17747v1 Announce Type: cross Abstract: Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure. A high score should mean the judge checked the faulty step against the run (a cross-…
- arXiv cs.AIagentsDegrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
arXiv:2610.17751v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but…
- arXiv cs.AIagentsGaussian Process Bandits for AI System Optimization with Selectively Verified Feedback
arXiv:2610.17760v1 Announce Type: cross Abstract: Gaussian process bandits exploit similarities among configurations to optimize prompts, retrieval systems, and agent workflows. In these applications, however, inexpensiv…
- arXiv cs.AIagentsAgentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design
arXiv:2610.17832v3 Announce Type: replace-cross Abstract: Materials and chemical optimization must choose the next synthesis, characterization, or high-fidelity simulation from sequential observations under a limited bud…
- arXiv cs.AIagentsProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?
arXiv:2610.17837v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limited coverage of exploitation that depends on inter…
- arXiv cs.AIagentsInteraction-as-a-Judge
arXiv:2610.17895v3 Announce Type: replace-cross Abstract: Coding agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applic…
- arXiv cs.AIagentsDriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving
arXiv:2610.17903v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) and world models have demonstrated strong capabilities in semantic understanding and future scene evolution for autonomous driving. However,…
- arXiv cs.AIagentsGLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigation
arXiv:2610.17927v1 Announce Type: cross Abstract: Autonomous navigation in real-world environments often requires long-horizon operation under partial observability and evolving goals. Existing mapless navigation approac…
- arXiv cs.AIagentsSWEPatchTest: Evaluating Software Tests Beyond Reproduction
arXiv:2610.18004v1 Announce Type: cross Abstract: Coding agents use generated tests to decide whether a proposed patch satisfies an issue's requirements. A suite that fails on the buggy program and passes after applying…
- arXiv cs.AIagentsCost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests
arXiv:2610.18007v1 Announce Type: cross Abstract: LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send externally visible emails on behalf of a user. Existing…
- arXiv cs.AIagentsLatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent Systems
arXiv:2610.18014v1 Announce Type: cross Abstract: Non-prefix KV cache reuse is a promising approach for improving inference efficiency in multi-agent systems as agents share the same context blocks. However, when agents…
- arXiv cs.AIagentsAPT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
arXiv:2610.18097v1 Announce Type: cross Abstract: Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We…
- arXiv cs.AIagentsFan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables
arXiv:2610.18157v1 Announce Type: cross Abstract: Inside organizations, a question's data often sit with several owners, who query their own tables but never hand them over. An LLM coordinator can fan out, sending the qu…
- arXiv cs.AIagentsTextualRL: Textual Reinforcement Learning for Context Management
arXiv:2610.18216v1 Announce Type: cross Abstract: LLM agents can adapt to task feedback by revising the textual context that guides their behavior, without changing their model parameters. However, turning execution rewa…
- arXiv cs.AIagentsHolding Agents Accountable with Verifiable Agent Insurance
arXiv:2610.18230v1 Announce Type: cross Abstract: While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused on preventing such…