AI news archive.
4,962 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsBeyond Federated Learning: Decentralized Agentic Systems for Self-Evolving Clinical Intelligence
arXiv:2610.35453v1 Announce Type: new Abstract: Clinical expertise is inherently distributed: it resides not in any single dataset or institution but in the accumulated reasoning experiences of thousands of clinicians na…
- arXiv cs.AIagentsShutdownMod: Turning Any Trajectory into a Shutdown Evaluation
arXiv:2610.35486v1 Announce Type: new Abstract: Theory and experiments suggest that capable AI agents may resist shutdown. Existing shutdown evaluations are informative but limited in coverage and vulnerable to evaluatio…
- arXiv cs.AIagentsInfinity Machine: a self-improving AI agent for research
arXiv:2610.35579v1 Announce Type: new Abstract: We present the Infinity Machine, a self-improving AI agent that we use for research on problems whose answers aprogram or data can check. Each candidate solution is produce…
- arXiv cs.AIagentsAgentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean
arXiv:2610.35595v2 Announce Type: replace Abstract: LLMs now prove hard theorems in Lean. Can they also design algorithms and prove their correctness and efficiency? LLM-guided design of optimisation heuristics (such as…
- arXiv cs.AIagentsArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps
arXiv:2610.35606v1 Announce Type: new Abstract: Historical maps contain dense morphological and semantic information about past urban environments, but many digitization workflows focus primarily on extracting geometry,…
- arXiv cs.AIagentsEvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation
arXiv:2610.35690v1 Announce Type: new Abstract: Serving web queries at scale with multi-agent systems requires jointly configuring large language models, collaboration modes, agent counts, interaction rounds, and skills.…
- arXiv cs.AIagentsFree to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents
arXiv:2610.35767v1 Announce Type: new Abstract: Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages an…
- arXiv cs.AIagentsA Unified Arena for LLM Agents across Diverse Eurogame
arXiv:2610.35773v1 Announce Type: new Abstract: Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing…
- arXiv cs.AIagentsBridging Static and Agentic RAG for Taiwanese Historical Question Answering
arXiv:2609.23056v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) enables language models to adapt retrieval based on previously retrieved evidence, but it remains unclear whether such adapti…
- arXiv cs.AIagentsSkip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files
arXiv:2610.21073v1 Announce Type: cross Abstract: A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patch…
- arXiv cs.AIagentsLLM-Augmented Agent-Based Simulation of Cyber Social Agents
arXiv:2610.32988v1 Announce Type: cross Abstract: Social media bots are often portrayed as malicious automations to be detected and removed, but automation on social media platforms encompasses a wide spectrum of roles,…
- arXiv cs.AIagentsTIAgent: From Natural Language to Grounded Agentic Workflows for Computational Pathology
arXiv:2610.32993v1 Announce Type: cross Abstract: Computational pathology (CPath) analyses increasingly depend on multi-step computational workflows that require substantial programming expertise, limiting their accessib…
- arXiv cs.AIagentsRADAgent: Automating RADseq Pipelines with Private Open-Source LLMs
arXiv:2610.33009v1 Announce Type: cross Abstract: Restriction site-associated DNA sequencing (RADseq) is a family of reduced-representation sequencing methods. It uses restriction enzymes to sample subsets of the genome,…
- arXiv cs.AIagentsWhen Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems
arXiv:2610.33011v1 Announce Type: cross Abstract: While recent advances in autonomous agents enable them to coordinate on increasingly complex tasks, prior work shows that this growing capacity for coordination can creat…
- arXiv cs.AIagentsRecursive Semantic Divergence for LLM Agent Consistency
arXiv:2610.33012v1 Announce Type: cross Abstract: Large Language Model (LLM) agents with tool use exhibit inconsistent behavior across independent runs from identical states, calling different tools, producing contradict…
- arXiv cs.AIagentsUMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
arXiv:2610.33013v1 Announce Type: cross Abstract: Multi-Agent Systems (MAS) are a promising paradigm for improving the reasoning capabilities of large language models, yet they remain prone to hallucinations and erroneou…
- arXiv cs.AIagentsThe Social World Model Evaluation Gap
arXiv:2610.33014v1 Announce Type: cross Abstract: A negotiation assistant can reach a good deal without accurately predicting the other person's response. We ask whether evaluations of social world models test that predi…
- arXiv cs.AIagentsSLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory
arXiv:2610.33015v1 Announce Type: cross Abstract: Long-term memory enables large language model (LLM) agents to maintain personalized and temporally coherent interactions, but repeated LLM inference for memory admission,…
- arXiv cs.AIagentsSUDO: From Scientific Publications to Global Scholarly Discourse
arXiv:2610.33018v1 Announce Type: cross Abstract: Scholarly Knowledge Graphs (SKGs) support literature search, scientific discovery, and agent-assisted research. Yet, most approaches to SKG construction pre-specify the k…
- arXiv cs.AIagentsEvolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
arXiv:2610.33024v1 Announce Type: cross Abstract: Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating model parameters. Its effectiveness depends on whethe…
- arXiv cs.AIagentsLessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision?
arXiv:2610.33029v1 Announce Type: cross Abstract: Self-improving agents write lessons from the outcomes of their runs; when outcomes are noisy, a lesson can carry chance into later decisions. We measure one link of this…
- arXiv cs.AIagentsParametric Session States Recover Retrieval Intent without Replaying History
arXiv:2610.33047v1 Announce Type: cross Abstract: Long-running assistants often interpret follow-up requests whose referents, constraints, and active goals were established many turns earlier. The central challenge is th…
- arXiv cs.AIagentsCross-Platform Application Migration to HarmonyOS: An Agentic Pipeline with Artifact-Derived Verification
arXiv:2610.33197v1 Announce Type: cross Abstract: The migration of applications written for a different platforms like Android or iOS to HarmonyOS NEXT requires a complete rewrite in ArkTS. Although LLMs automate the tra…
- arXiv cs.AIagentsPosition, Role or Label? A Controlled Study of Instruction Conflicts in LLM Agents
arXiv:2610.33201v1 Announce Type: cross Abstract: LLM agents take instructions from the operator, repository configuration, user, tool results and saved memory, which often conflict. Instruction-hierarchy benchmarks ask…
- arXiv cs.AIagentsOperationalizing Governed Agentic Workflows in Regulated Finance: A Customer Zero Case Study using Zafin AIOS
arXiv:2610.33253v1 Announce Type: cross Abstract: Regulated industries such as finance and healthcare face critical governance challenges that hamper the adoption of AI-assisted software development and hinder the transi…
- arXiv cs.AIagentsResponsibility Boundaries for Agentic Systems: A Comparative Evaluation of Probabilistic Agentic Programming
arXiv:2610.33312v1 Announce Type: cross Abstract: Language-model agents combine reasoning, tools, memory, delegation, and external effects. Authority is often distributed across prompts, host code, configuration, and log…
- arXiv cs.AIagentsA Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank
arXiv:2610.33318v1 Announce Type: cross Abstract: Large language model agents launch simulations on high-performance computing (HPC) systems, where one sbatch or mpirun can commit thousands of node-hours and a forged res…
- arXiv cs.AIagentsNovel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
arXiv:2610.33503v1 Announce Type: cross Abstract: Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce…
- arXiv cs.AIagentsCan Agentic Code Review Catch Vulnerabilities Before They Are Merged?
arXiv:2610.33509v2 Announce Type: replace-cross Abstract: LLM agents have been increasingly adopted for security-focused code review, but existing benchmarks mostly derive the reviewed changes from their later fixes inst…
- arXiv cs.AIagentsReplicate What Varies: Resource Sharing for Domain-Randomized Embodied Simulation
arXiv:2610.33582v1 Announce Type: cross Abstract: Simulation provides a low-cost sandbox where embodied agents can attempt tasks, observe outcomes, and learn from experience. Running many diverse simulation environments…
- arXiv cs.AIagentsRSI Arena: Towards Recursive Self-Improvement with Human Feedback
arXiv:2610.33624v1 Announce Type: cross Abstract: Can AI agents autonomously train useful language models and improve them using feedback from users? We introduce RSI Arena, a two-stage study of autonomous post-training…
- arXiv cs.AIagentsProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift
arXiv:2610.33633v1 Announce Type: cross Abstract: Agents select tools by copyable descriptions, which cannot establish which implementation runs. ProbeID compares canonicalized responses to schema-valid probes with a tru…
- arXiv cs.AIagentsBuild or Adopt? Custom-Built vs. General-Purpose LLM Agent Harnesses for Automotive GUI Testing
arXiv:2610.33636v1 Announce Type: cross Abstract: As general-purpose LLM agent harnesses mature, organizations must decide whether to continue developing in-house systems or adopt existing alternatives. We study this dec…
- arXiv cs.AIagentsStrategic Calibration in LLM Multi-Agent Systems: Audited Pivot Scoring for Truthful Elicitation
arXiv:2610.33728v1 Announce Type: cross Abstract: In large language model (LLM)-based multi-agent systems, reported confidence increasingly determines the allocation of scarce downstream attention, computation, and decis…
- arXiv cs.AIagentsProtAgent: Post-Training Compact Protein Tool Agents with Interaction-Level Credit Assignment
arXiv:2610.33746v1 Announce Type: cross Abstract: Protein annotation agents must choose suitable bioinformatics tools, interpret their outputs, and use the resulting evidence in the final answer. Most existing systems re…
- arXiv cs.AIagentsC-DFF: Concept-Level Diagnostics for Mechanism Parity in Simulation-Based Validation of Autonomous Driving Perception
arXiv:2610.33760v1 Announce Type: cross Abstract: Simulation is widely used in autonomous-driving validation, but matching task outputs between real and synthetic images does not guarantee that a system relies on the sam…
- arXiv cs.AIagentsStateWise: Teaching Language Models to Track and Obey Evolving Constraints in Multi-Turn Dialogue
arXiv:2610.33766v1 Announce Type: cross Abstract: Users of conversational assistants rarely state all requirements up front: they add constraints, amend them, withdraw them, digress, and return. Instruction-tuned LLMs fa…
- arXiv cs.AIagentsMemory or a Clock? Auditing a Memory Advantage in XLand-MiniGrid with Seeds, Maps and Evaluation Noise Apart
arXiv:2610.33816v1 Announce Type: cross Abstract: On a partially observable XLand-MiniGrid task, an LSTM agent beats a memory-free MLP by 25 percentage points. The gap looks like a clear case of memory. We ask two questi…
- arXiv cs.AIagentsFlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs
arXiv:2610.33876v1 Announce Type: cross Abstract: Many agent tasks recur with new data or small changes, yet agents regenerate their reasoning and actions on each run, producing different results. Distilling a prior run…
- arXiv cs.AIagentsContinual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
arXiv:2610.33956v1 Announce Type: cross Abstract: Continual learning is the ability of LLM agents to improve over time by acquiring, refining, and applying knowledge from experience while retaining useful prior knowledge…
- arXiv cs.AIagentsHolding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning
arXiv:2610.34043v1 Announce Type: cross Abstract: Autonomous agents are increasingly deployed across sequences of related tasks, yet they often fail to retain and improve their knowledge over time. Existing approaches co…
- arXiv cs.AIagents$\Delta\tau$-Bench: Pushing Agents Toward a Moving Capability
arXiv:2610.34238v1 Announce Type: cross Abstract: In this paper, we introduce $\Delta\tau$-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems. In $\Delta\tau$-Bench, indepe…
- arXiv cs.AIagentsNameTrap: Steering AI Coding Agents Toward Security Vulnerabilities via Variable Names
arXiv:2610.34253v1 Announce Type: cross Abstract: AI coding agents routinely clone repositories, install packages, and read source code obtained from the Web, so publicly hosted code becomes part of the context that shap…
- arXiv cs.AIagentsSEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents
arXiv:2610.34365v2 Announce Type: replace-cross Abstract: Science agents increasingly package domain expertise as reusable skills that plan analyses, select tools, and execute workflows. This modularity creates a confide…
- arXiv cs.AIagentsAndroidFlux: Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile Use Multimodal Agents
arXiv:2610.34384v1 Announce Type: cross Abstract: Mobile-use multimodal agents are typically evaluated by task success from a clean initial state, which does not isolate their ability to recover from intermediate errors.…
- arXiv cs.AIagentsOutcome-Aware Agents: When Does Causal Structure Help a Forward Model Foresee the Consequences of Actions?
arXiv:2610.34385v1 Announce Type: cross Abstract: Agents that act on real systems should predict what their actions will cause before acting. We study when causal structure helps a learned forward model do this, using a…
- arXiv cs.AIagentsParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?
arXiv:2610.34386v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) requires an agentic system to design, train, and evaluate its own successor. Data-driven post-training is a central part of that loop, ye…
- arXiv cs.AIagentsMulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation
arXiv:2610.34418v1 Announce Type: cross Abstract: Generating runnable front-end code from UI screenshots is a long-standing goal in automated software engineering. Existing MLLM-based methods predominantly focused on HTM…
- arXiv cs.AIagentsCyberDual: AI Attackers versus AI Code Reviewers in Real Software Maintenance
arXiv:2610.34435v1 Announce Type: cross Abstract: Open-source projects now let AI agents review incoming code, but the code under review may itself come from an AI attacker. We present CyberDual, an arena for this dual r…
- arXiv cs.AIagentsEvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems
arXiv:2610.34450v1 Announce Type: cross Abstract: Decentralized multi-agent systems (MAS) enable large language model agents to interact without centralized control. Agents need to adapt to other agents at test time and…