AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsWhat the Trace Shows and What the Label Says: Auditing Behavioral Detectors in Agent Evaluation
arXiv:2610.30491v1 Announce Type: new Abstract: LLM agents are often evaluated by reducing execution traces to labels such as final-answer correctness, tool verification, and fault propagation. These labels are measureme…
- arXiv cs.AIagentsFrom Prose to Properties: Testing Research Claims with ARATest for Agent-Native Science
arXiv:2610.30495v1 Announce Type: new Abstract: AI agents now run experiments and report findings, so research produces claims faster than researchers can check them. Each empirical claim implies a property that must hol…
- arXiv cs.AIagentsPLE: Physical-Engineering's Last Exam
arXiv:2610.30537v1 Announce Type: new Abstract: Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no exi…
- arXiv cs.AIagentsGoverned Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core
arXiv:2610.30557v1 Announce Type: new Abstract: LLM agents that act on live Web data must combine heterogeneous evidence, remember what they have done and improve from outcomes without weakening their own safeguards. We…
- arXiv cs.AIagentsDiagnosing Personalization Failures in Mobile GUI Agents
arXiv:2610.30573v1 Announce Type: new Abstract: Unlike conventional GUI agents, personalized GUI agents require user preferences to guide sequential execution over changing GUI states. This raises two challenges: determi…
- arXiv cs.AIagentsBetter Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference
arXiv:2610.30611v1 Announce Type: new Abstract: Scaling large language models has substantially improved linguistic fluency, yet reliable autonomous agents require more than fluent generation. In multi-turn inference, cu…
- arXiv cs.AIagentsAnticipating Social Consequences with Distributional World Models
arXiv:2610.30657v1 Announce Type: new Abstract: Social world models predict how interactions develop after an action, helping agents negotiate, cooperate and mediate. In these situations, one action can lead to several p…
- arXiv cs.AIagentsA Topology-Guided GeoAI Agentic Framework for Urban Flood Screening
arXiv:2610.30660v1 Announce Type: new Abstract: Open-world geographic artificial intelligence (GeoAI) agents can transform public geospatial data into accessible decision support for real-world challenges, but must balan…
- arXiv cs.AIagentsGovernance-State Corruption in Long-Term Memory for LLM Agents: A Cross-Model Stress Test
arXiv:2610.30698v1 Announce Type: new Abstract: An LLM agent can retrieve a memory correctly yet use it incorrectly after its validity state changes. We study governance-state corruption: faults that alter which retained…
- arXiv cs.AIagentsAgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes
arXiv:2610.30738v1 Announce Type: new Abstract: When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the rele…
- arXiv cs.AIagentsIs Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
arXiv:2610.30755v1 Announce Type: new Abstract: LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or othe…
- arXiv cs.AIagentsAgentDP: Towards Automated Model Deployment for Heterogeneous Embedded AI Applications
arXiv:2610.30760v1 Announce Type: new Abstract: This paper presents AgentDP, which aims to deploy pre-trained AI models on heterogeneous embedded devices by fully automating model optimization and adaptation (O&A) with L…
- arXiv cs.AIagentsLLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades
arXiv:2610.30769v1 Announce Type: new Abstract: Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vu…
- arXiv cs.AIagentsAn Introduction to World Models for Generalist Agents
arXiv:2610.30789v1 Announce Type: new Abstract: World models have recently emerged as a promising direction toward developing generalist agents capable of understanding, predicting, and interacting with diverse environme…
- arXiv cs.AIagentsAgentic Knowledge-Model Co-Evolution via Consistency Regularization
arXiv:2610.30790v1 Announce Type: new Abstract: LLM agents can evolve by learning from accumulated experience. Existing approaches extract reusable external knowledge, such as skills and memories, from experience to guid…
- arXiv cs.AIagentsADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization
arXiv:2610.30851v1 Announce Type: new Abstract: Scientific discovery often requires identifying a small number of high-performing designs in vast, constrained search spaces. This is difficult when evaluations are costly,…
- arXiv cs.AIagentsHarnessing Language Models as Optimization Modeling Agents
arXiv:2610.30917v1 Announce Type: new Abstract: Large language models (LLMs) can translate natural-language optimization problems into solver programs, but reliably producing correct formulations and implementations rema…
- arXiv cs.AIagentsColaBench: Evaluating Memory-Guided Knowledge Acquisition in Personal Agents
arXiv:2610.30989v1 Announce Type: new Abstract: Personal agents need to draw on long-term interaction history to retrieve and apply external knowledge suited to a user's current request. Even an answer grounded in releva…
- arXiv cs.AIagentsCANNBot-CAKE: Collaborative Agentic Kernel Evolution for Ascend NPU
arXiv:2610.31034v1 Announce Type: new Abstract: Efficient custom operators are essential for modern deep learning workloads, yet developing high-performance kernels for Ascend NPUs remains slow, expert-intensive, and dif…
- arXiv cs.AIagentsSCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs
arXiv:2610.31062v1 Announce Type: new Abstract: Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-…
- arXiv cs.AIagentsDual Exam: Controlled Evaluation of Multimodal Agents and World Models
arXiv:2610.31066v2 Announce Type: replace Abstract: World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interac…
- arXiv cs.AIagentsWho Is the Influencer? Consensus Dynamics in Multi-Agent Systems
arXiv:2610.31105v1 Announce Type: new Abstract: Multi-agent LLM systems are increasingly used in practice, but their behavior is complex and hard to understand. We design a simple task to ask which model has the most inf…
- arXiv cs.AIagentsCan AI Co-Design Structures? An AI Agent for Early-Stage Structural Design
arXiv:2610.31113v1 Announce Type: new Abstract: Recent advances in large language models and agentic workflows offer a new paradigm to early-stage structural design translating design intent into structural models. Altho…
- arXiv cs.AIagentsPost-Audit Mirage: Identifiability Limits of Offline Agent Verification
arXiv:2610.31130v1 Announce Type: new Abstract: Offline tests can fail to reveal whether an agent update will remain safe after deployment. We operationalize this post-audit mirage using matched safe and harmful lifecycl…
- arXiv cs.AIagentsPointerBench: A Diagnostic Benchmark for Fine-Grained GUI Grounding
arXiv:2610.31274v1 Announce Type: new Abstract: Multimodal Large Language Models have shown promising performance in computer-use tasks, from planning user workflows to grounding natural-language actions to precise UI ta…
- arXiv cs.AIagentsRIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding
arXiv:2610.31276v1 Announce Type: new Abstract: Long-horizon coding agents can observe a failure and generate a plausible critique yet continue along the same incorrect trajectory. We call this the Critique-to-Action Han…
- arXiv cs.AIagentsThe Value of Memory in Language Agents
arXiv:2610.31303v2 Announce Type: replace Abstract: Memory enables language agents to carry useful distinctions from past experience into future decisions. Its value depends on which distinctions survive, whether a bound…
- arXiv cs.AIagentsSubgoal-aware Memory Graph for GUI Agent
arXiv:2610.31307v1 Announce Type: new Abstract: GUI agents aim to automate complex user tasks by interacting with mobile interfaces, but ef- fective decision-making in long-horizon set- tings requires reusing prior exper…
- arXiv cs.AIagentsMuffin - A Shared Memory Buffer for Asynchronous AI Agents
arXiv:2610.31355v1 Announce Type: new Abstract: The rise of Agentic AI systems has changed the landscape of artificial intelligence by enabling strong reasoning capabilities through specialized multi-agent interaction wi…
- arXiv cs.AIagentsRIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention
arXiv:2610.31372v2 Announce Type: replace Abstract: Autonomous research agents are increasingly used to automate large portions of scientific research, yet they are prone to research integrity violations (RIVs): behavior…
- arXiv cs.AIagentsCertified Execution Harness for Agentic AI: Safe and Least-Intrusive Petri-Net Supervisory Control Between Reasoning and Action
arXiv:2610.31376v1 Announce Type: new Abstract: This paper studies the problem of safe tool execution for large language model (LLM) agents under prompt injection. Using Petri nets, we formalize the execution harness bet…
- arXiv cs.AIagentsConservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity
arXiv:2610.31436v1 Announce Type: new Abstract: Automated agentic-system design is typically evaluated on static task suites with immediate scalar rewards. Deployed systems face persistent shift, delayed dependent feedba…
- arXiv cs.AIagentsAdaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery
arXiv:2610.31461v1 Announce Type: new Abstract: Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely s…
- arXiv cs.AIagentsDuoCook: An Overcooked-Inspired Benchmark for Visual Planning and Coordination
arXiv:2610.31511v1 Announce Type: new Abstract: Coordinating two players in a cooking task requires a vision-language agent to track changing scene states, sequence recipe steps, and allocate shared resources under a tim…
- arXiv cs.AIagentsContestable Agents for Data Governance: Recording Human Stewardship of AI-Generated Metadata Across Structured and Unstructured Systems
arXiv:2610.31553v1 Announce Type: new Abstract: Industrial organizations hold operational knowledge in structured records, such as telemetry, point lists, and transactions, and in unstructured sources, such as manuals, s…
- arXiv cs.AIagentsEpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence
arXiv:2610.31650v1 Announce Type: new Abstract: Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry…
- arXiv cs.AIagentsLighthouse: On Building a Trustworthy Digital Assistant for Exploring History with Civil Rights Archives
arXiv:2610.30158v1 Announce Type: cross Abstract: Artificial intelligence (AI), as a decision-support aid, provides new tools for studying history effectively using multimodal data, including text, images, and audio. We…
- arXiv cs.AIagentsTauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents
arXiv:2610.30161v1 Announce Type: cross Abstract: Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blockin…
- arXiv cs.AIagentsIRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization
arXiv:2610.30167v1 Announce Type: cross Abstract: Optimizing Information Retrieval (IR) pipelines for Retrieval-Augmented Generation (RAG) requires jointly selecting structural components and numerical hyperparameters un…
- arXiv cs.AIagentsAgentic Verified Optimization of Real-World Software
arXiv:2610.30188v1 Announce Type: cross Abstract: Program optimization aims to improve performance while preserving behavior. Coding agents can already make programs faster by changing algorithms, data structures, and ex…
- arXiv cs.AIagentsSWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents
arXiv:2610.30284v1 Announce Type: cross Abstract: Coding agents spend substantial computation generating actions and processing long interaction histories. Poor action choices can steer agents into low-value states, wast…
- arXiv cs.AIagentsGAV: A scientific experimentation environment for PDE agents
arXiv:2610.30292v1 Announce Type: cross Abstract: Reliable feedback is essential for coding agents to develop programs for partial differential equations (PDEs). Yet evaluating these programs on new PDE problems often re…
- arXiv cs.AIagentsTerraTransfer++: Demonstration-Free End-to-End Planner
arXiv:2610.30319v1 Announce Type: cross Abstract: End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive acro…
- arXiv cs.AIagentsMemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments
arXiv:2610.30379v1 Announce Type: cross Abstract: LLM agents are flexible in language interaction, but using them as long-horizon planners is costly and prone to hallucinated or invalid actions. This paper targets a diff…
- arXiv cs.AIagentsAgent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
arXiv:2610.30418v1 Announce Type: cross Abstract: Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled from them. This mosaic effect creates a critical…
- arXiv cs.AIagentsSelf-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models
arXiv:2610.30435v1 Announce Type: cross Abstract: Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search…
- arXiv cs.AIagentsSplatLab: Autonomous Scientific Discovery for 3DGS Research
arXiv:2610.30468v1 Announce Type: cross Abstract: Reproducing a published 3DGS paper takes weeks of expert engineering before any extension can be proposed. Prior autonomous-research systems read papers, draft hypotheses…
- arXiv cs.AIagentsExternalise the Memory: A Pre-Registered Study of Where an Embodied Agent's Experience Should Live
arXiv:2610.30478v1 Announce Type: cross Abstract: Should an embodied agent's experience be baked into its policy weights, or kept external and retrieved at inference? A memory-augmented teacher (a VLM that retrieves less…
- arXiv cs.AIagentsDecision Making and Ride Comfort Evaluation Based on Lane-Change Prediction for Autonomous Vehicles
arXiv:2610.30528v1 Announce Type: cross Abstract: Predicting surrounding vehicles' lane-change intentions enables autonomous vehicles to anticipate potential hazards and respond proactively rather than relying solely on…
- arXiv cs.AIagentsLifetime-valid decisions by continually evolving AI analysts
arXiv:2610.30562v1 Announce Type: cross Abstract: AI agents increasingly act as analysts whose decision can often be cast as hypothesis tests. Classical tests control the Type I error rate, the probability of rejecting a…