AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsReducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning
arXiv:2508.08882v5 Announce Type: replace Abstract: Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning sy…
- arXiv cs.AIagentsLLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
arXiv:2508.17692v2 Announce Type: replace Abstract: Recent advances in LLM-based agents highlight the importance of their reasoning frameworks, which guide the problem-solving process in diverse ways. This survey introdu…
- arXiv cs.AIagentsAstroAgentBench: Evaluating Agentic Planning on Space Mission Planning Tasks
arXiv:2601.11354v3 Announce Type: replace Abstract: Recent LLM-for-Space systems address mission planning, scheduling, operations support, simulator control, and autonomy, but their evaluations use different task contrac…
- arXiv cs.AIagentsWhy Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory
arXiv:2601.22984v3 Announce Type: replace Abstract: Diagnosing failure patterns in Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evaluation, obscuring inte…
- arXiv cs.AIagentsPhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
arXiv:2602.13691v2 Announce Type: replace Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However, long-horizon multi-…
- arXiv cs.AIagentsDetecting Multi-Agent Collusion Through Multi-Agent Interpretability
arXiv:2604.01151v5 Announce Type: replace Abstract: Non-verbalised or secret collusion may impose a ceiling on transcript-level monitoring in multi-agent deployments. Internal model activations are known to provide an ad…
- arXiv cs.AIagentsThe Hitchhikers Guide to Rubric Quality Understanding and Enrichment
arXiv:2604.01375v4 Announce Type: replace Abstract: Rubrics distill notions of expert quality and measure agent performance. However, the quality of rubrics themselves have not been systematically measured and are often…
- arXiv cs.AIagentsSpatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks
arXiv:2604.12102v3 Announce Type: replace Abstract: We describe compute-grounded reasoning (CGR), a design pattern in which code computes selected sub-problems from explicit intermediate representations before a language…
- arXiv cs.AIagentsSWE-chat: Coding Agent Interactions From Real Users in the Wild
arXiv:2604.20779v2 Announce Type: replace Abstract: AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We prese…
- arXiv cs.AIagentsSkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
arXiv:2605.08386v2 Announce Type: replace Abstract: Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single…
- arXiv cs.AIagentsRMA: Context-Orchestrated Research Math Agents
arXiv:2605.22875v2 Announce Type: replace Abstract: Long-horizon mathematical reasoning fails less often because a model cannot produce a valid next step than because an agent fails to maintain and expose the right seman…
- arXiv cs.AIagentsArchitect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
arXiv:2606.10953v2 Announce Type: replace Abstract: Furnished floor plans support real-estate visualization, interior design, and architectural workflows, yet automatic furnishing remains challenged by limited real-world…
- arXiv cs.AIagentsSeparating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deployment
arXiv:2607.01674v4 Announce Type: replace Abstract: In multi-source ECG deployment, new sources may arrive when earlier raw ECGs cannot be retained or replayed. Isolating source-specific classifiers on a frozen backbone…
- arXiv cs.AIagentsSemantic Cooperative Games for Contribution Attribution in LLM-Based Multi-Agent Systems
arXiv:2607.18255v2 Announce Type: replace Abstract: Contribution attribution has become a central problem in LLM-based multi-agent systems, where final outputs are produced through multiple agents, message exchanges, and…
- arXiv cs.AIagentsESCROW: Guarded and Dual-Objective Continual Maintenance for Agents in Policy-Governed Enterprise Workflows
arXiv:2608.01772v2 Announce Type: replace Abstract: LLM agents increasingly run policy-bound enterprise workflows, where they must apply rules consistently and stay auditable. Deploying such an agent is the start of its…
- arXiv cs.AIagentsFinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
arXiv:2608.06144v2 Announce Type: replace Abstract: Agents used over time encounter recurring professional work: each case requires different evidence and judgment, while the underlying workflow can be reused. Benchmarks…
- arXiv cs.AIagentsiARCS: Iterative Agentic RL for Controllable 3D Scene Generation
arXiv:2608.06161v3 Announce Type: replace Abstract: Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism witho…
- arXiv cs.AIagentsSE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
arXiv:2609.08228v2 Announce Type: replace Abstract: LLM agents use large libraries of reusable skills. At thousands of skill entries, retrieval becomes the bottleneck. Graph-of-Skills (GoS) retrieves dependency-aware bun…
- arXiv cs.AIagentsKernel-Managed Shared Memory for System-Wide Personalization
arXiv:2609.10144v3 Announce Type: replace Abstract: AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often remains unavailable to…
- arXiv cs.AIagentsTRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
arXiv:2603.21152v4 Announce Type: replace-cross Abstract: Modern seismic networks resolve earthquake sequences in unprecedented detail, yet explaining how large earthquakes emerge from evolving fault systems remains diff…
- arXiv cs.AIagentsROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents
arXiv:2606.00341v2 Announce Type: replace-cross Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safety considerat…
- arXiv cs.AIagentsSPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering
arXiv:2606.00593v3 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-h…
- arXiv cs.AIagentsAligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual Pacts
arXiv:2606.08081v2 Announce Type: replace-cross Abstract: Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific expressions grounded in shared intera…
- arXiv cs.AIagentsDecentralized Multi-Agent Systems with Shared Context
arXiv:2606.10662v3 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) can scale large language model agents on long-horizon tasks by running them in parallel, yet existing designs waste much of this paralle…
- arXiv cs.AIagentsFalse Prophets: On the Security of World Models in Agentic Systems
arXiv:2607.23147v2 Announce Type: replace-cross Abstract: Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of these tasks r…
- arXiv cs.AIagentsThe Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark
arXiv:2608.11469v2 Announce Type: replace-cross Abstract: AI agents are rapidly improving in cybersecurity when source code is available, yet much of the software most consequential to security, including malware, firmwa…
- arXiv cs.AIagentsGenerative Interpretability via Scalable Neuro-Symbolic Models
arXiv:2609.13529v2 Announce Type: replace-cross Abstract: As the use of Large Language Models moves from chatbots into agentic systems, where outputs become actions with irreversible consequences on reality, the existing…
- AI BusinessagentsMeta expands Muse to small businesses
The move comes as agentic AI plays an increasingly big part in business operations, sparking oversight concerns.
- AWS Machine Learning BlogagentsScaling cloud migrations with agentic AI on Amazon Bedrock AgentCore
Learn how AWS Professional Services uses a multi-agent framework built on Amazon Bedrock AgentCore to automate enterprise cloud migrations end to end. Purpose-built AI agents handle discovery, infrastructure as code gene…
- WIRED AIagentsTrump’s ‘Morally Binding’ AI ‘Accord,’ the Rise of AI Agents, and Extremists on the Ballot
This week on “Uncanny Valley,” we discuss the voluntary AI safety agreement tech executives signed, AI agents for normies, and extremist candidates running for office in the US midterms.
- SiliconANGLE AIagentsIBM allows on-prem deployment of its Bob agentic development platform
IBM Corp. today announced a self-hosted deployment option for IBM Bob, its agentic software development platform, allowing enterprises to use artificial intelligence to build and modernize applications within their own i…
- SiliconANGLE AIagentsAlways-on AI agents turn infrastructure into a continuous learning loop
AI agent infrastructure is evolving to support systems that move continuously among inference, feedback and training. Cognition AI Inc.’s Devin now assists throughout the software development lifecycle, from planning and…
- NVIDIA Developer BlogagentsBuild Applications on NVIDIA BlueField Faster with NVIDIA DOCA Agent Skills
AI agents are becoming a standard part of development workflows, but general-purpose agents weren't built with specialized infrastructure software such as...
- AWS Machine Learning BlogagentsBuild agent memory with NVIDIA NeMo Agent Toolkit and Amazon S3 Vectors
Learn how to use Amazon S3 Vectors as the persistent memory layer within the NVIDIA NeMo Agent Toolkit (NAT), deployed on Amazon Elastic Kubernetes Service (Amazon EKS). This post shows how NAT's memory subsystem works a…
- TechCrunch AIagentsShopify debuts Canvas, a way to build online stores by chatting with AI
Shopify’s new Canvas site builder lets merchants create and customize their online stores by chatting with its AI agent Sidekick, while watching the changes happen in real time.
- AWS Machine Learning BlogagentsBuilding ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows
Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on Amazon Bedrock AgentCore u…
- AWS Machine Learning BlogagentsImplementing Multi-Environment Access for Claude Platform on AWS
Learn how to configure secure, multi-environment access to Claude Platform on AWS from a single subscription: cross-account SigV4 for AWS workloads, workspace-scoped API keys for developers, and OIDC federation for exter…
- The Register AI + MLagentsAWS offers local, open source leash for agent harnesses
Dogwood Local Engine checks AI tool calls against user-defined temporal rules before they run
- OpenAI NewsagentsHow Albertsons Companies is reimagining retail from the inside out
Albertsons Cos. is using ChatGPT Enterprise and the OpenAI API to help teams work faster and make grocery shopping easier for millions of customers.
- TechCrunch AIagentsBrian Chesky interview: AI agents need their own operating system
Brian Chesky on making Airbnb agent-friendly, the state of consumer AI, and why the world needs an AI-native operating system.
- TechRadar AIagents‘The era of the agentic enterprise isn't coming, it's here’: Snowflake lays out what is business needs to be truly agentic
Mainstream AI news from a large tech publication.
- The Verge AIagentsOpenAI’s new agent is a shot at Meta — but can it compete with free?
At OpenAI's annual DevDay conference, the company pulled out all the stops to compete with its rivals - primarily Meta, whose Muse AI agent platform has seen early runaway success. CEO Sam Altman walked onstage to cheers…
- TechCrunch AIagentsPhoton held a funeral for mobile apps. Now it has $4.5M to help replace them with agents.
The startup helps developers build AI agents that work over iMessage, SMS/RCS, email, and other messaging platforms. It's a bet that consumers will increasingly use agents instead of downloading apps.
- LessWrongagentsHow many AI agents are running unattended right now?
There are 8 billion human minds running in the world right now. Recently a new digital species has emerged. How many digital minds are there alive in the world right now? Define a digital mind to be an AI agent that runs…
- SiliconANGLE AIagentsServiceNow launches conversational interface to its service desk
ServiceNow Inc. is enhancing the artificial intelligence features in its service desk offering with Flow, a feature that handles employee requests via a natural language interface with extensive automation. The company s…
- TechRadar AIagentsAI agents are ready to act, but do they understand your business?
Mainstream AI news from a large tech publication.
- The Register AI + MLagentsThe tech industry is hot for shopping bots, but they're years away
What's good for human shoppers does not work with probabilistic AI agents
- Tom's Guide AIagents7 boring jobs you can hand to an AI agent tonight — number 4 is my personal favorite
Consumer AI launches, tools, and practical coverage.
- arXiv cs.AIagentsAREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
arXiv:2609.38288v1 Announce Type: new Abstract: We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This abil…
- arXiv cs.AIagentsMoFlow: Multi-Objective Agentic Workflow Generation
arXiv:2609.38294v1 Announce Type: new Abstract: We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. Existing methods for w…