AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsGeneral Collaborative Intelligence: Architecting Cognition for Resilient Multi-Agent Ecosystems
arXiv:2609.22967v1 Announce Type: cross Abstract: Multi-agent unmanned systems are moving from isolated, ego-centric sensing toward collaborative intelligence, in which distributed agents exchange compact features to ove…
- arXiv cs.AIagentsAutomatic multimodal UX improvement recommendations from LLM agent user simulations
arXiv:2609.22971v1 Announce Type: cross Abstract: Evaluating user experience (UX) on live websites through user testing is expensive, subjective, and difficult to scale. LLM agents offer a promising route to automating U…
- arXiv cs.AIagentsAuditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity
arXiv:2609.23039v1 Announce Type: cross Abstract: LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their behavior is dynamic…
- arXiv cs.AIagentsDiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation
arXiv:2609.23103v1 Announce Type: cross Abstract: While simulation-ready deformable assets are essential for in-silico robotic manipulation tasks, existing generation frameworks typically assess physical plausibility aft…
- arXiv cs.AIagentsMM-ContextFold: Context Folding for Multimodal Agentic Retrieval
arXiv:2609.23121v2 Announce Type: replace-cross Abstract: Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical frameworks such as R…
- arXiv cs.AIagentsLLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication
arXiv:2609.23193v1 Announce Type: cross Abstract: As Large Language Model (LLM) APIs become increasingly integrated into privacy-sensitive workflows, ensuring inference-time privacy without compromising task utility rema…
- arXiv cs.AIagentsTriggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents
arXiv:2609.23215v1 Announce Type: cross Abstract: LLM explainers are increasingly attached to autonomous agents as runtime oversight, with operators reading a generated account of the agent's beliefs and actions rather t…
- arXiv cs.AIagentsSemantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval
arXiv:2609.23307v1 Announce Type: cross Abstract: This paper presents a comparative evaluation of dense embedding models for semantic candidate-job matching in high-volume staffing workflows. Incoming job descriptions ar…
- arXiv cs.AIagentsGraph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines
arXiv:2609.23315v1 Announce Type: cross Abstract: Graph databases are frequently positioned as categorically necessary for connected-data workloads, yet the systems dimension along which they actually differ - query plan…
- arXiv cs.AIagentsHuman-guided physics-constrained AI agents construct an auditable model of soil-plug evolution
arXiv:2609.23360v1 Announce Type: cross Abstract: Engineering predictions require physical mechanisms to be translated consistently into equations, discretization, code, and validation, yet errors can propagate despite l…
- arXiv cs.AIagentsOmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents
arXiv:2609.23407v2 Announce Type: replace-cross Abstract: Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for embodied agents…
- arXiv cs.AIagentsWaveletECO: A Closed-Loop Physical ECO Platform and a Specialized Local Language Model
arXiv:2609.23444v1 Announce Type: cross Abstract: Engineering change order (ECO) is an important step in repairing timing and electrical violations during the late stages of chip design. Existing Agentic EDA methods prim…
- arXiv cs.AIagentsPropose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations
arXiv:2609.23465v2 Announce Type: replace-cross Abstract: Memory enables language model agents to use information beyond their context windows, but maintaining and accessing this information reliably remains difficult. L…
- arXiv cs.AIagentsRPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
arXiv:2609.23466v2 Announce Type: replace-cross Abstract: Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, m…
- arXiv cs.AIagentsCE$^4$L: Continual Ego, Exo, and Ego-Exo Learning
arXiv:2609.23492v1 Announce Type: cross Abstract: Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shifts. Yet continual…
- arXiv cs.AIagentsSemDHT: Certified Semantic Discovery for Peer-to-Peer Agent Networks over Exact-Key DHTs
arXiv:2609.23539v1 Announce Type: cross Abstract: Agents may need capabilities exposed through external agent endpoints or service APIs. When a requester is not already bound to a provider, it must discover advertised ca…
- arXiv cs.AIagentsModeling Clinical Workflow for SYNTAX Scoring from Coronary Angiography Videos
arXiv:2609.23553v1 Announce Type: cross Abstract: The SYNTAX score is a clinically established tool for assessing anatomical lesion complexity in coronary artery disease and guiding subsequent treatment. However, automat…
- arXiv cs.AIagentsSpiking Neural Network Actor-Critic Proximal Policy Optimization Control for Autonomous UAV Navigation Through Constrained Openings in Civil Infrastructure and Buildings
arXiv:2609.23643v1 Announce Type: cross Abstract: Autonomous navigation of unmanned aerial vehicles in constrained three-dimensional environments has been a challenge in the robotics domain. The application of autonomous…
- arXiv cs.AIagentsWhen the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems
arXiv:2609.23700v1 Announce Type: cross Abstract: Large language model agents are now privileged principals that take consequential actions: editing code repositories, operating inboxes, completing purchases. Their autho…
- arXiv cs.AIagentsFLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model
arXiv:2609.23808v1 Announce Type: cross Abstract: While test-time scaling enhances Large Language Model (LLM) agents in long-horizon software engineering (SWE), sparse binary rewards (Pass/Fail) create a severe credit as…
- arXiv cs.AIagentsVISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking
arXiv:2609.23875v1 Announce Type: cross Abstract: The rapid growth of resident space objects is increasing the complexity of space situational awareness sensor tasking, challenging classical optimization methods as they…
- arXiv cs.AIagentsConnecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges
arXiv:2609.23894v1 Announce Type: cross Abstract: Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other agents. Existing threat…
- arXiv cs.AIagentsMCPGen: Benchmarking LLMs on Executable MCPWorkflow Development
arXiv:2609.23925v1 Announce Type: cross Abstract: We study whether LLMs can produce executable workflow artifacts that remain consistent across graph structure, tool implementation, schema bindings, and runtime wiring. I…
- arXiv cs.AIagentsMobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes
arXiv:2609.23980v1 Announce Type: cross Abstract: AI agents now report vulnerabilities faster than maintainers can review them. Reports often depend on security properties specific to the application, and require conside…
- arXiv cs.AIagentsWidgetVA: A Widget-Centric Framework and Benchmark for Agentic Visual Analytics
arXiv:2609.24094v1 Announce Type: cross Abstract: Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level intents into long seque…
- arXiv cs.AIagentsReinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective
arXiv:2609.24103v1 Announce Type: cross Abstract: In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. We address both form…
- arXiv cs.AIagentsAction-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding
arXiv:2609.24127v1 Announce Type: cross Abstract: Atomic activity understanding aims to recognize and localize structured traffic behaviors that jointly encode motion patterns and their grounding in road topology. Unlike…
- arXiv cs.AIagentsData Agents: Agentic Data Systems
arXiv:2609.24137v1 Announce Type: cross Abstract: Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating…
- arXiv cs.AIagentsMCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents
arXiv:2609.24161v1 Announce Type: cross Abstract: As LLM agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet underexplored factor. How…
- arXiv cs.AIagentsMemCalib: Benchmarking and Optimizing Memory Use in LLM Agents
arXiv:2609.24259v3 Announce Type: replace-cross Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over its respon…
- arXiv cs.AIagentsTTSE: A Two-Track Online Self-Evolution Framework
arXiv:2609.24289v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents are applied in continuously interactive environments, driving the evolution of their own capabilities becomes a core problem for achi…
- arXiv cs.AIagentsA Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach
arXiv:2609.24348v1 Announce Type: cross Abstract: AI coding agents increasingly support software development beyond code completion, including planning, implementation, testing, and repository-level task execution. Their…
- arXiv cs.AIagentsDissecting Agentic Forensics: The Role of Triage, Prompting, and Evidence Arbitration in Open-World Fake Image Detection
arXiv:2609.24359v1 Announce Type: cross Abstract: Image forensics is increasingly an open-world problem: manipulations range from fully synthetic images to localized edits, splicing and swapping, while most forensic dete…
- arXiv cs.AIagentsActGov: Governing LLM Agent Actions via Policy-Constrained Validation
arXiv:2609.24446v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions a…
- arXiv cs.AIagentsAgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos
arXiv:2609.24487v1 Announce Type: cross Abstract: In this work, we present a method for shape reconstruction and tracking from video via agentic analysis-by-synthesis. Unlike prior methods which first estimate dense pixe…
- arXiv cs.AIagentsBeyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
arXiv:2609.24515v1 Announce Type: cross Abstract: AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly impor…
- arXiv cs.AIagentsFrom Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking
arXiv:2609.24631v2 Announce Type: replace-cross Abstract: Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics and collisio…
- arXiv cs.AIagentsTrust in Edge-Enabled IoT Security: Features, Challenges and Research Directions
arXiv:2609.24669v1 Announce Type: cross Abstract: Providing autonomous intelligence, pervasive connectivity and usability to human life and industry has led to the emergence of the Internet of Things (IoT). To support ti…
- arXiv cs.AIagentsLLM-based Conversational AI Knowledge Assistant for MyBuddy Humanoid Robot
arXiv:2609.24742v1 Announce Type: cross Abstract: Humanoid robots are increasingly being popular and developed for human-centered applications, yet their ability to provide intelligent conversations and natural interacti…
- arXiv cs.AIagentsPrismGPT: Proxy-Guided Learning for Region-Aware Photo Editing with Self-Synthesized Reasoning
arXiv:2609.24768v1 Announce Type: cross Abstract: Professional photo finishing relies on both global adjustments and region-specific local edits guided by semantic masks, yet current automated methods handle this workflo…
- arXiv cs.AIagentsSmall-world Networks of Agents Brainstorm AI Risks to Support Ideation
arXiv:2609.24859v1 Announce Type: cross Abstract: The ideation phase of participatory AI risk assessment often starts with a blank slate or a limited list of predefined risks, making it difficult to surface indirect or s…
- arXiv cs.AIagentsWhen Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting
arXiv:2609.24862v1 Announce Type: cross Abstract: Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning strategies, and inte…
- arXiv cs.AIagentsOSWorld-Pro: Process-based Evaluation for Computer Use Agents
arXiv:2609.24890v1 Announce Type: cross Abstract: Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with functional verifiers,…
- arXiv cs.AIagentsJev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences
arXiv:2609.24965v4 Announce Type: replace-cross Abstract: Scientific workflows often require choosing among known relations before a deterministic calculation can proceed. Whether observations share a culture, treatment…
- arXiv cs.AIagentsRare Event Estimation via Iterative Unalignment
arXiv:2609.24969v1 Announce Type: cross Abstract: As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic. Safe deployment th…
- arXiv cs.AIagentsDolphinBench: Mapping the Pareto Frontier of Agent Memory
arXiv:2609.24971v2 Announce Type: replace-cross Abstract: Agents today often take real-world actions that depend on long-term memory and context recall over time. However, most current memory benchmarks are built for a c…
- arXiv cs.AIagentsRRSI: Regularized Recursive Self-Improvement of Agent Harnesses
arXiv:2609.24972v3 Announce Type: replace-cross Abstract: An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen ba…
- arXiv cs.AIagentsControlling risks of AI in chemical science with agents
arXiv:2312.06632v2 Announce Type: replace Abstract: Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful substances, or circumventi…
- arXiv cs.AIagentsDivide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
arXiv:2505.13994v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy trade-offs when scaling…
- arXiv cs.AIagentsPADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork
arXiv:2511.07260v3 Announce Type: replace Abstract: Ad hoc teamwork (AHT) requires agents to collaborate with previously unseen teammates, which is crucial for many real-world applications. The core challenge of AHT is t…