AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsMulti-Agent Egocentric World Model with Fine-Grained Embodied Interaction
arXiv:2610.12299v1 Announce Type: cross Abstract: Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multip…
- arXiv cs.AIagentsRoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
arXiv:2610.12424v1 Announce Type: cross Abstract: A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks c…
- arXiv cs.AIagentsTelling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
arXiv:2610.12445v4 Announce Type: replace-cross Abstract: Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via…
- arXiv cs.AIagentsFrom Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. Open…
- arXiv cs.AIagentsThought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Bootstrapped Prolog-based Chain-of-Thought
arXiv:2407.14562v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities as general-purpose assistants, excelling in a wide range of reasoning tasks and supporting various aspec…
- arXiv cs.AIagentsAgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System
arXiv:2507.14897v3 Announce Type: replace Abstract: Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL). However, agentic RL remains b…
- arXiv cs.AIagentsNeural Architecture Discovery via Autonomous Evolution
arXiv:2507.18074v2 Announce Type: replace Abstract: Recent progress in LLM agents has advanced the prospect of autonomous research. Yet whether AI can complete difficult long-horizon tasks, especially those that advance…
- arXiv cs.AIagentsMAPF-World: Action World Model for Multi-Agent Path Finding
arXiv:2508.12087v3 Announce Type: replace Abstract: Multi-agent path finding (MAPF) studies the problem of planning conflict-free paths for multiple agents from given start locations to designated goals, with application…
- arXiv cs.AIagentsMore Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
arXiv:2510.04532v2 Announce Type: replace Abstract: Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning…
- arXiv cs.AIagentsProof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
arXiv:2510.10931v3 Announce Type: replace Abstract: While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacki…
- arXiv cs.AIagentsMobileWorldBench: Towards Semantic World Modeling For Mobile Agents
arXiv:2512.14014v2 Announce Type: replace Abstract: World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approach…
- arXiv cs.AIagentsAgentic Critical Training
arXiv:2603.08706v2 Announce Type: replace Abstract: Imitation learning (IL) teaches language-model agents to reproduce expert actions but not to distinguish them from plausible mistakes. Self-reflection methods expose mo…
- arXiv cs.AIagentsBeyond Preset Identities: Selective Stance Accommodation and Interaction Reorganisation in Generative Agent Societies
arXiv:2603.23406v4 Announce Type: replace Abstract: Generative agent societies simulate people with assigned roles, preferences and relationships. As agents exchange arguments and choose partners, they can revise their p…
- arXiv cs.AIagentsLiteGUI: Lightweight GUI Agents via Multi-Solution Guided Distillation and Dual-Level Reinforcement Learning
arXiv:2605.07505v2 Announce Type: replace Abstract: We present LiteGUI, a new framework for building lightweight GUI agents. GUI interaction poses unique challenges due to the long-horizon nature of complex tasks and the…
- arXiv cs.AIagentsMedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
arXiv:2605.11814v2 Announce Type: replace Abstract: The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking.…
- arXiv cs.AIagentsEgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
arXiv:2605.27820v2 Announce Type: replace Abstract: As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and…
- arXiv cs.AIagentsSAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing
arXiv:2607.13594v2 Announce Type: replace Abstract: LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a guard model that la…
- arXiv cs.AIagentsMasked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
arXiv:2607.16204v2 Announce Type: replace Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward di…
- arXiv cs.AIagentsCompute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV
arXiv:2607.23693v2 Announce Type: replace Abstract: Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest. Eviction and episodic-memory sche…
- arXiv cs.AIagentsBeyond Component Testing: Validating Agentic AI Systems
arXiv:2607.29405v2 Announce Type: replace Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This behavior stretches validation practice…
- arXiv cs.AIagentsCRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Driving
arXiv:2608.09202v2 Announce Type: replace Abstract: Modern autonomous vehicles are equipped with multiple sensors, such as cameras, LiDAR, and radar, for comprehensive environmental perception. However, robust cross-moda…
- arXiv cs.AIagentsDoes Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf
arXiv:2608.22697v5 Announce Type: replace Abstract: When shopping is delegated to AI agents, it is unclear whether the ranking advantage documented for humans persists. Across 7,000 sessions with five large language mode…
- arXiv cs.AIagentsA Score Is Not a Policy: Measuring the Value of Adaptive Revision
arXiv:2609.00874v2 Announce Type: replace Abstract: As agentic systems become compound systems, increasingly important decisions move above task execution itself: when should a higher-level controller preserve the strate…
- arXiv cs.AIagentsPolicy Learning with a Language Bottleneck
arXiv:2405.04118v4 Announce Type: replace-cross Abstract: Modern AI systems such as self-driving cars and game-playing agents can achieve superhuman performance, but often lack human-like generalization, interpretability…
- arXiv cs.AIagentsAttention when you need
arXiv:2501.07440v3 Announce Type: replace-cross Abstract: Paying attention improves performance, but attention is metabolically costly, so how should a resource-efficient agent allocate it? We study optimal allocation st…
- arXiv cs.AIagentsSimultaneous Computation with Multiple Prioritizations in Multi-Agent Motion Planning
arXiv:2501.10781v2 Announce Type: replace-cross Abstract: Multi-agent path finding (MAPF) in large networks is computationally challenging. An approach for MAPF is prioritized planning (PP), in which agents plan sequenti…
- arXiv cs.AIagents\$OneMillion-Bench: How Far are Language Agents from Human Experts?
arXiv:2603.07980v2 Announce Type: replace-cross Abstract: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confi…
- arXiv cs.AIagentsArbiter: Detecting Interference in LLM Agent System Prompts
arXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to conventional software…
- arXiv cs.AIagentsBridging the Last Mile of Circuit Design: PostEDA-Bench, a Hierarchical Benchmark for PPA Convergence and DRC Fixing
arXiv:2605.06936v4 Announce Type: replace-cross Abstract: LLM-based agents are increasingly applied to the "last mile" of Electronic Design Automation (EDA): repairing residual sign-off Design Rule Check (DRC) violations…
- arXiv cs.AIagentsVISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents
arXiv:2605.26144v4 Announce Type: replace-cross Abstract: Coding agents can now build applications from design mockups, but a screen that looks right is not an application that works. Existing benchmarks either score vis…
- arXiv cs.AIagentsRight Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
arXiv:2606.10388v4 Announce Type: replace-cross Abstract: A skill can match a task's topic while conflicting with its resource, procedure, or output requirements. We study this as same-capability risk-exposure retrieval…
- arXiv cs.AIagentsThe Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
arXiv:2606.26294v3 Announce Type: replace-cross Abstract: Self-improving agents are state-of-the-art on agentic coding benchmarks, yet their search methods assume a stationary evaluation criterion. This ignores a central…
- arXiv cs.AIagentsBeyond Direct Access: Resource Hijacking in LLM Agents
arXiv:2608.15108v2 Announce Type: replace-cross Abstract: Large language model agents are increasingly connected to high-value resources, including external APIs, GPUs and servers, and workflows such as deployment and ap…
- arXiv cs.AIagentsX2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR
arXiv:2609.08672v4 Announce Type: replace-cross Abstract: Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low commit latency…
- arXiv cs.AIagentsSalesforce Koa: An Enterprise Language Model for Agentic Tool Use
arXiv:2609.15066v2 Announce Type: replace-cross Abstract: We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcement learning…
- AI BusinessagentsGoogle’s workplace agent is out, but questions abound
The agent can use enterprise business context for knowledge work. However, questions about cost and integration with other tools could be difficult for enterprises.
- The Verge AIagentsInstinct was the buzziest AI agent around — can it survive Muse?
Before there were cute little guys, there was Instinct. In August, the startup got its AI agent to market with an unusual playbook: invite-only, no marketing, and barely so much as a website. And yet, Instinct quickly be…
- SiliconANGLE AIagentsCoreWeave Forge aims to speed up the AI improvement loop
Enterprises racing to put agents into production are learning that the AI improvement loop never really ends. Agents must be run, observed, evaluated and improved continuously. CoreWeave Inc. has been assembling a full-s…
- NVIDIA BlogagentsInto the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents
Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and checking that the scene behaves as intended. Developers are combining frontier AI models with NVIDIA Omn…
- The Register AI + MLagentsThere can be only one: Google Cloud casts Gemini as your enterprise AI hero
The Chocolate Factory proposes a single universal agent for work
- AWS Machine Learning BlogagentsPay-per-inference for AI agents: How BlockRun and Incarna use Amazon Bedrock AgentCore payments
Amazon Bedrock AgentCore payments gives AI agents a managed way to pay for services on demand, with spending limits enforced by the infrastructure. See how Incarna's agents pay BlockRun for model inference one request at…
- NVIDIA Developer BlogagentsBuilding Reliable Data Analytics Agents: Lessons from the KDD Cup
The NVIDIA KGMON team placed second in the KDD Cup 2026 Data Agents competition with a system built around a simple idea of making an agent's harness smaller,...
- TechCrunch AIagentsGoogle brings agentic AI to Gemini, starting with businesses
Google is turning Gemini into an AI agent that can plan, execute tasks, and work across business apps and systems. The agent can delegate work to subagents, use multiple AI models, and even gets its own workplace identit…
- TechCrunch AIagentsNatura’s $99 smart ring puts AI agents on your finger
Natura’s $99 Interface smart ring lets you summon AI agents with the press of a finger to complete tasks, capture thoughts, and control devices — while doubling as a health tracker.
- OpenAI NewsagentsHow Oracle turns days of work into minutes with ChatGPT and Codex
Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.
- The Verge AIagentsGoogle is launching a one-stop Gemini agent for your work tasks
Google is launching a "universal" Gemini AI agent that can work across apps and devices in the background. The tool, announced as part of the Gemini at Work event on Thursday, will be available within the Gemini Enterpri…
- The Verge AIagentsCan you trust Meta’s Muse or OpenAI’s Dots to run your life?
My Decoder guest today is Hayden Field, The Verge’s senior AI reporter, and we’re discussing the new wave of consumer-friendly AI agents. If you’ve been paying attention to this space, you know AI enthusiasts have been u…
- TechRadar AIagentsTop Goldman Sachs executive says new workers will be managing 'virtual army' of AI from the moment they start
Mainstream AI news from a large tech publication.
- Google Cloud AI & Machine LearningagentsWelcome to Gemini at Work 2026: Introducing the Gemini agent
By Thomas Kurian • 29-minute read
- SiliconANGLE AIagentsGoogle Cloud introduces Gemini agent to change enterprise work
Google LLC’s Cloud division today introduced Gemini agent, a unified artificial intelligence assistant that can act autonomously, generate code and complete work across any device, including web, mobile and desktop. The…