AI news archive.
4,958 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsIn-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents
arXiv:2610.41291v1 Announce Type: cross Abstract: Long-horizon LLM agents play an important role in solving complex and sustained tasks, with ever-growing interaction contexts. However, these accumulated contexts will ra…
- arXiv cs.AIagentsART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control
arXiv:2610.41304v1 Announce Type: cross Abstract: Particle image velocimetry (PIV) measures fluid motion from images of tracer particles, but its accuracy depends on choices throughout the estimation pipeline, including…
- arXiv cs.AIagentsWhen Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing
arXiv:2610.41401v1 Announce Type: cross Abstract: Large language model agents interact with online services through tool calls that may access private data or perform sensitive actions. Specialized providers can supply a…
- arXiv cs.AIagentsBlindToChange: AI Agents Can Find Changes When Asked But Do They Look When Needed?
arXiv:2610.41435v1 Announce Type: cross Abstract: Given that AI agents can search the web broadly and deeply in real time, it is tempting to conclude that their outputs account for recent world events. We show that this…
- arXiv cs.AIagentsKEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents
arXiv:2610.41482v1 Announce Type: cross Abstract: Recursive textual memory can carry earlier errors into later updates, yet task performance alone does not establish memory reliability. We define self-consistency bias as…
- arXiv cs.AIagentsLatent-Lens: Visual Perception in Small Language Models Through Latent Communication
arXiv:2610.41751v1 Announce Type: cross Abstract: Bridging independent vision-language models (VLMs) and small language models (SLMs) in a modular multi-agent system typically forces them to exchange information as discr…
- arXiv cs.AIagentsSimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI
arXiv:2610.41856v1 Announce Type: cross Abstract: Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based res…
- arXiv cs.AIagentsSecPO: Principled Adversarial Training for Prompt Injection Security
arXiv:2610.41998v1 Announce Type: cross Abstract: Recognized as a top threat to AI agents, prompt injection allows instructions from untrusted data (email, documents, websites) to manipulate the agent's operation. The ex…
- arXiv cs.AIagentsRoboArchitect: Automating the Design of Robotic Agents with Persistent Memory
arXiv:2610.42141v1 Announce Type: cross Abstract: Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or co…
- arXiv cs.AIagentsHierarchical World Models with Implicit Dynamics
arXiv:2610.42146v1 Announce Type: cross Abstract: Planning with world models enables test-time adaptation for embodied agents, offering superior generalization over direct policy learning. However, long-horizon tasks rem…
- arXiv cs.AIagentsAx-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
arXiv:2510.12787v5 Announce Type: replace Abstract: We present Ax-Prover, a multi-agent system for automated theorem proving in Lean that can solve problems across diverse scientific domains and operate either autonomous…
- arXiv cs.AIagentsSoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
arXiv:2603.07379v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems are increasingly evolving into agentic architectures where large language models autonomously coordinate multi-step reasoni…
- arXiv cs.AIagentsControllable User Simulation
arXiv:2605.11519v2 Announce Type: replace Abstract: Using offline datasets to evaluate conversational agents often fails to cover rare scenarios or to support testing new policies. This has motivated the use of controlla…
- arXiv cs.AIagentsPhysics-Audited Agentic Discovery in Scientific Machine Learning
arXiv:2607.07379v2 Announce Type: replace Abstract: Agentic discovery can yield mechanics surrogates with low validation error that nonetheless violate physical requirements. We present Physics-Audited Agentic SciML (PA-…
- arXiv cs.AIagentsOpen Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
arXiv:2603.15080v4 Announce Type: replace-cross Abstract: Biomedical knowledge is fragmented across siloed databases---Reactome, STRING, Gene Ontology, ClinicalTrials.gov, DrugBank, DGIdb, SIDER, PubMed, ClinVar, ChEMBL,…
- arXiv cs.AIagentsSTRIATUM-CTF: A Protocol-Driven Agentic Framework for Autonomous CTF Solving
arXiv:2603.22577v2 Announce Type: replace-cross Abstract: Autonomous cyber operations increasingly depend on agents that can chain reconnaissance, exploitation, and analysis across many tools while maintaining state over…
- arXiv cs.AIagentsM$^\star$: Every Task Deserves Its Own Memory Harness
arXiv:2604.11811v3 Announce Type: replace-cross Abstract: Large language model agents rely on a memory harness to write, organize, retrieve, and use past experience. A harness that works for one task often fails on anoth…
- arXiv cs.AIagentsEvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
arXiv:2605.18421v3 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it en…
- arXiv cs.AIagentsGUI-Lens: Enabling Precise GUI Grounding for Off-the-Shelf VLMs via Coarse-to-Fine Cropping
arXiv:2608.03270v2 Announce Type: replace-cross Abstract: GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, dense…
- arXiv cs.AIagentsTamilEOT: A Dataset and Model for Semantic End-of-Turn Detection in Tamil Telephone Speech
arXiv:2609.05631v2 Announce Type: replace-cross Abstract: A voice agent must decide, at each pause, whether the speaker has finished or is still thinking. Without a model of the language, systems fall back to a fixed sil…
- Apple Machine Learning ResearchagentsOnline Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live iOS Apps
While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via supervised fine-tuning (SF…
- The DecoderagentsGoogle wants video AI to understand what people need as they work
A Google-led research team built StreamVibe, a video agent designed to watch people cook or assemble furniture and speak up only when help is needed. A benchmark shows that none of the tested models reliably pick the rig…
- Latent SpaceagentsAgents Prompt People: Using Agents for Long-Horizon Financial Work
Arca's head of AI discusses persistent memory, the benefits of a custom harness, and agentic workflows that span days.
- WIRED AIagentsMeta’s Muse Could Upend All Kinds of Businesses. It Hasn’t Yet
Companies have spent the past several weeks trying to reassure investors that Muse and other AI agents pose more of an opportunity than a threat.
- WIRED AIagentsAn AI Agent Injected Drugs Into a Live Mouse’s Brain
A biotech startup let an agent choose a gene therapy and successfully inject the treatment, offering a startling glimpse of the future of research labs.
- AWS Machine Learning BlogagentsPreview web apps live as your coding agent builds them with Amazon Bedrock AgentCore runtime
Amazon Bedrock AgentCore Session endpoints give each runtime session an authenticated URL that forwards any HTTP method, path, and WebSocket connection to the ports you allow. In this post, you deploy a coding agent that…
- The DecoderagentsA Claude model autonomously chose a gene therapy and operated on a mouse brain with no human decision-making
An AI agent performed brain surgery on an epileptic mouse, picking the drug, the brain target, and the injection coordinates on its own. According to lead researcher Ocana-Santero, it's the first time an AI agent has aut…
- Ars Technica AIagentsBasically no one is using AI agents for their DoorDash orders
But it’s still early days for the relatively new e-commerce use case.
- TechCrunch AIagentsZest’s new AI agent finds restaurants and books reservations over text
Can't agree on where to eat? Zest's AI concierge can combine everyone's tastes, put restaurant options to a vote, and make the reservation.
- The Verge AIagentsStarbucks wants to use AI to show you a ‘personalized digital menu’ at the drive-thru
Starbucks could eventually show you a personalized digital menu when you pull up to the drive-thru. During an earnings call on Thursday, Starbucks CEO Brian Niccol said the company is going to explore "experiences that r…
- AWS Machine Learning BlogagentsHow Worldwide Express automated freight exceptions with Amazon Bedrock
Worldwide Express automated its less-than-truckload freight billing-exception process with a multi-agent solution built on Amazon Bedrock. Six months after launch, the company cut active exceptions by 75%, improved time-…
- AWS Machine Learning BlogagentsConfigure the ChatGPT desktop app with Amazon Bedrock in AWS GovCloud (US)
The ChatGPT desktop app is now available on Amazon Bedrock in AWS GovCloud (US). This post walks through a controlled local deployment that routes model inference to Amazon Bedrock in AWS GovCloud (US-West) using API-mod…
- TechRadar AIagentsCounting agents is the wrong scoreboard: Better questions for enterprise leaders
Mainstream AI news from a large tech publication.
- TechRadar AIagentsAmazon CEO Andy Jassy says he isn't worried about 'still not great' shopping agents and bots rendering the site useless
Mainstream AI news from a large tech publication.
- NVIDIA Developer BlogagentsBuild Specialized Agents on a Stack You Control with NVIDIA NemoClaw
Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces...
- TechCrunch AIagentsDoorDash said it’s only received ‘several hundred’ orders from AI agents
DoorDash said that it is open to working with third-party agent makers.
- SiliconANGLE AIagentsThe race to deploy AI agents finds a familiar hurdle in data access
Enterprises racing to put AI agents into production are discovering that role-based access control, not model choice, decides whether those agents can be trusted. Rising inference costs, privacy worries and sovereignty d…
- SiliconANGLE AIagentsAI agents cut critical research time for humanitarian teams in conflict zones
Humanitarian groups working in conflict zones are finding that agentic AI can shorten the research cycle between a crisis and an informed response. Cloudera Inc. has built its AI strategy around deployment flexibility, a…
- The Register AI + MLagentsAccenture AI agents are sifting through applicants
But a human makes final hiring decisions at global tech consultancy
- TechRadar AIagentsHow to use AI agents to handle marketing, meetings, invoices, and inventory
Mainstream AI news from a large tech publication.
- arXiv cs.AIagentsWebAnything: From the Wild Web to Scalable Agent Environments
arXiv:2610.37786v1 Announce Type: new Abstract: Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, wh…
- arXiv cs.AIagentsWhat Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs
arXiv:2610.37809v1 Announce Type: new Abstract: LLM agents that answer questions over Web knowledge graphs are increasingly wrapped in checks derived from the graph's ontology, on the assumption that a formal schema make…
- arXiv cs.AIagentsMeasuring Where Intent Gets Lost in Agentic Smart Contract Synthesis
arXiv:2610.37830v1 Announce Type: new Abstract: AI agents can now write software from a plain-English description, but code that runs is not the same as code that does what was asked. This gap matters most for smart cont…
- arXiv cs.AIagentsDetecting Covert Collusion between AI Agents through Partner-Outsider Positive Listening
arXiv:2610.37849v1 Announce Type: new Abstract: AI agents that share a secret convention can coordinate through messages that look innocent, so a monitor that reads only the messages can miss them. We propose a behaviour…
- arXiv cs.AIagentsEvaluating and improving AI agents for sequencing protocol understanding
arXiv:2610.37851v1 Announce Type: new Abstract: Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocol…
- arXiv cs.AIagentsSeq@K: Evaluating Language Models Under Sequential Feedback
arXiv:2610.37859v1 Announce Type: new Abstract: Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iter…
- arXiv cs.AIagentsFilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision
arXiv:2610.37905v1 Announce Type: new Abstract: Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents req…
- arXiv cs.AIagentsSciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World
arXiv:2610.37919v1 Announce Type: new Abstract: Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of p…
- arXiv cs.AIagentsGARDEN: Generalist Autonomous Reward Design Through Evidence Navigation for Cooperative Multi-Agent Reinforcement Learning
arXiv:2610.37926v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning (MARL) enables teams of agents, such as robots and autonomous vehicles, to learn coordinated behavior, but what such teams le…
- arXiv cs.AIagentsSkillMem: Compact External Skill Memory for Latent Multi-Agent Reasoning
arXiv:2610.37935v1 Announce Type: new Abstract: Latent multi-agent systems reduce inference cost by keeping intermediate reasoning and inter-agent communication in continuous representations.\ Reusable skills, however, a…