AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?
arXiv:2610.07792v1 Announce Type: cross Abstract: Large language model agents are increasingly deployed to perform complex tasks in real-world environments. However, the knowledge required for correct behavior in these e…
- arXiv cs.AIagentsThe Geometry of Empowerment
arXiv:2610.07796v2 Announce Type: replace-cross Abstract: Empowerment captures the capacity for an agent to actively control its environment. While conceptually appealing as an information-theoretic quantity, the connect…
- arXiv cs.AIagentsOne Step at a Time: Trading LLM Autonomy for Process Predictability
arXiv:2610.07817v1 Announce Type: cross Abstract: Organizations automating operational processes need more than a correct outcome: they need to predict how a process will run, know which one actually ran, and inspect it…
- arXiv cs.AIagentsHarness Engineering for Software Engineering via Modular Executable Dev-Primitives
arXiv:2610.07832v1 Announce Type: cross Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain…
- arXiv cs.AIagentsA self-learning scientific agent for X-ray diffraction
arXiv:2610.07862v1 Announce Type: cross Abstract: A central challenge for scientific agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-lear…
- arXiv cs.AIagentsReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessio…
- arXiv cs.AIagentsDecide Before You Look: Learning Which Retrieved Memories Deserve Pixels
arXiv:2610.07984v1 Announce Type: cross Abstract: Multimodal assistants answer questions from long-term memories that contain images. After retrieval, each retrieved image reaches the answering model either as pixels, at…
- arXiv cs.AIagentsWhen Tools Lie: Reliability of Mathematical Agents Under Corrupted Tool Feedback
arXiv:2610.08097v1 Announce Type: cross Abstract: Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicitly trust. Yet tools can fail silently, returning p…
- arXiv cs.AIagentsToken-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor
arXiv:2610.08155v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative…
- arXiv cs.AIagentsTool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek
arXiv:2610.08205v1 Announce Type: cross Abstract: Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-augmented generation…
- arXiv cs.AIagentsMitigating Concept Drift in QoS Prediction for Teleoperation of Autonomous Vehicles Using Historic Data
arXiv:2610.08297v1 Announce Type: cross Abstract: Teleoperation serves as the fallback solution to autonomous driving but reliable functions of the teleoperation require a certain amount of mobile network resources, whic…
- arXiv cs.AIagentsTransferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving
arXiv:2610.08331v1 Announce Type: cross Abstract: The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies. While ad…
- arXiv cs.AIagentsNeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
arXiv:2610.08430v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) disaggregates training from rollout, so each policy update must reach the rollout clusters before the next batch. Transferring a full…
- arXiv cs.AIagentsWiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World Discussions
arXiv:2610.08513v1 Announce Type: cross Abstract: LLMs are increasingly deployed as autonomous agents in social environments, making it critical to study their ability to faithfully simulate human interactions. Central t…
- arXiv cs.AIagentsOne for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control
arXiv:2610.08595v1 Announce Type: cross Abstract: Deep generative models often produce structured outputs composed of interacting components. Modelling these outputs with a single model requires learning both the compone…
- arXiv cs.AIagentsAgentic RCA for Internet-Scale Services Using Constrained Creativity
arXiv:2610.08622v1 Announce Type: cross Abstract: System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services. Ideally, we want a troubleshooting system to…
- arXiv cs.AIagentsA Case Study in Assuring AI-Written Software
arXiv:2610.08651v1 Announce Type: cross Abstract: Software-engineering agents can enable people without formal software training to build systems they could not otherwise implement and simultaneously can produce more cod…
- arXiv cs.AIagentsSemantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
arXiv:2610.08668v1 Announce Type: cross Abstract: Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks b…
- arXiv cs.AIagentsPrincipled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
arXiv:2610.08670v2 Announce Type: replace-cross Abstract: An agent that can say an action is wrong and then take it anyway is a different failure from one that does not know better, and evaluations of stated values canno…
- arXiv cs.AIagentsAdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
arXiv:2610.08773v1 Announce Type: cross Abstract: Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's…
- arXiv cs.AIagentsDrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search
arXiv:2507.07426v4 Announce Type: replace Abstract: Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning. However, their effectiveness remains…
- arXiv cs.AIagentsFRAGMENTA: Efficient End-to-end Fragmentation-based Generative Model with Agentic Tuning for Drug Lead Optimization in Small Data Regime
arXiv:2511.20510v3 Announce Type: replace Abstract: Molecule generation from extremely limited training data is a key challenge in drug discovery. Existing fragment-based methods are more suitable than atom-based approac…
- arXiv cs.AIagentsPrecomputing Multi-Agent Path Replanning Using Temporal Flexibility
arXiv:2601.04884v4 Announce Type: replace Abstract: Executing a multi-agent plan can be challenging when an agent is delayed, because this typically creates conflicts with other agents. So, we need to quickly find a new…
- arXiv cs.AIagentsLearning to Configure Agentic AI Systems
arXiv:2602.11574v5 Announce Type: replace Abstract: Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled tod…
- arXiv cs.AIagentsEgo2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
arXiv:2605.13335v2 Announce Type: replace Abstract: Embodied agents in household environments must plan under partial observation: they need to remember objects, track state changes, and recover when actions fail. Existi…
- arXiv cs.AIagentsVoluntary Collusion with Secret Tools in Competing LLM Agents
arXiv:2605.27593v2 Announce Type: replace Abstract: Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doi…
- arXiv cs.AIagentsCoding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
arXiv:2606.05647v2 Announce Type: replace Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools.…
- arXiv cs.AIagentsSubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
arXiv:2606.05761v3 Announce Type: replace Abstract: Persistent AI assistants, such as OpenClaw, accumulate large collections of related memories over long-term interactions. As these memories grow, they may reinforce one…
- arXiv cs.AIagentsOSGuard: A Benchmark for Safety in Computer-Use Agents
arXiv:2606.15034v3 Announce Type: replace Abstract: Computer-use agents can complete benign user instructions while violating important constraints of the user's environment. We introduce OSGuard, a dual-granularity benc…
- arXiv cs.AIagentsCalibration Is Not Control: Intervention Value for LLM-Agent Oversight
arXiv:2606.21399v2 Announce Type: replace Abstract: Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can differ in whether interve…
- arXiv cs.AIagentsCritic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
arXiv:2607.12397v2 Announce Type: replace Abstract: LLM agents operate in stateful environments, where a single erroneous step can waste limited interaction budget or cause irreversible effects before task failure become…
- arXiv cs.AIagentsUnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
arXiv:2609.09815v2 Announce Type: replace Abstract: Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the final answer, allocate…
- arXiv cs.AIagentsStabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization
arXiv:2511.20718v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-po…
- arXiv cs.AIagentsMiniScope: Authorizing Agents with Least-Privilege Permissions
arXiv:2512.11147v2 Announce Type: replace-cross Abstract: AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a critical security c…
- arXiv cs.AIagentsDual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks
arXiv:2603.04364v2 Announce Type: replace-cross Abstract: Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream archi…
- arXiv cs.AIagentsPC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner
arXiv:2603.10330v3 Announce Type: replace-cross Abstract: Autonomous driving in complex traffic requires planners that generalize beyond hand-crafted rules, motivating data-driven approaches that learn behavior from expe…
- arXiv cs.AIagentsPBT-Bench: Benchmarking AI Agents on Property-Based Testing
arXiv:2605.15229v4 Announce Type: replace-cross Abstract: Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a described issue…
- arXiv cs.AIagentsKadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat
arXiv:2605.18850v2 Announce Type: replace-cross Abstract: We introduce KadiAssistant, a privacy-by-design AI assistant integrated into the Kadi research data ecosystem, enabling researchers to efficiently access, aggrega…
- arXiv cs.AIagentsTo Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
arXiv:2605.18882v2 Announce Type: replace-cross Abstract: LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models from three f…
- arXiv cs.AIagentsTask diversity produces systematic transfer but inhibits continual reinforcement learning
arXiv:2606.00880v2 Announce Type: replace-cross Abstract: Continual reinforcement learning (RL) aims to produce agents that never stop adapting to new tasks. A key question is how this interacts with the diversity of tas…
- arXiv cs.AIagentsStrategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems
arXiv:2608.04265v2 Announce Type: replace-cross Abstract: LLM-agent evaluations commonly measure task success or agreement with a declared plan. In strategic cyber-physical systems, an architecture must also remain appro…
- arXiv cs.AIagentsCost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution under Analysis Budgets
arXiv:2609.04820v2 Announce Type: replace-cross Abstract: Sandbox execution and memory forensics are among the most constrained resources in malware triage. Static analysis can scale to millions of files, whereas dynamic…
- Engadget AIagentsCisco is bringing a new agentic framework to its Webex enterprise platform
Cisco's Dialog feature promises to turn "fragmented interactions into continuous customer relationships."
- SiliconANGLE AIagentsCaterpillar and CoreWeave shorten the learning loop for physical AI
Demand for new data centers, power plants and highways is fueling a construction boom, even as the industry wrestles with declining productivity and a shortage of skilled machine operators. Physical AI, which lets machin…
- AI BusinessagentsHumanoid hard sell: Building robots for the manufacturing age
Where humanoid publicity outpaces reality, why purpose-built machines deserve more attention and how the West can get automation onto the factory floor.
- SiliconANGLE AIagentsMeta teams up with Bret Taylor’s Sierra Technologies on new standards for AI agent commerce
Meta Platforms Inc. is partnering with Walmart Inc., Stripe Inc. and the enterprise artificial intelligence firm Sierra Technologies Inc. on the creation of new standards that will define how autonomous AI agents interac…
- Simon Willison's WeblogagentsOpenAI “rogue” agent activities found on Wikimedia projects
OpenAI “rogue” agent activities found on Wikimedia projects Given how tempting a target wikis are for rogue agent swarms, it's not a huge surprise that Wikipedia found evidence of that activity once they went looking: Th…
- SiliconANGLE AIagentsTransforming the data path: Dell’s new releases move enterprises closer to the agentic data center
AI is taking shape, moving from models that answer questions to models that can reason. Now models are powering the agentic era, and Dell Technologies Inc. has announced several extensions to its AI Data Platform designe…
- TechCrunch AIagentsThe next hurdle for AI agents: getting websites to let them in
Personal AI agents promise to shop, book flights, and make reservations for you. But deliberate blocks and anti-bot defenses are getting in the way, leaving consumers caught in the middle. A new standard aims to help.
- AWS Machine Learning BlogagentsBuilding a context-aware AI assistant on AgentCore and OpenClaw
Off-the-shelf AI assistants forget you between conversations. This post shows how to build a personal assistant that accumulates context using OpenClaw on Amazon Bedrock AgentCore runtime, with AgentCore memory turning d…