AI news archive.
4,962 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsWhere Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?
arXiv:2610.37276v1 Announce Type: cross Abstract: Large language model (LLM)-driven agent scaffold evolution improves agent workflows through iterative candidate generation and evaluation. Evaluation both guides subseque…
- arXiv cs.AIagentsAnalogScout: Simulation-Efficient PVT-Aware Analog Sizing with LLM Agents
arXiv:2610.37319v1 Announce Type: cross Abstract: Analog device sizing must satisfy all specifications across process, voltage, and temperature (PVT) corners to ensure tape-out success, but simulating every candidate at…
- arXiv cs.AIagentsFeatureArc: Benchmarking Coding Agents on Evolving Features
arXiv:2610.37434v1 Announce Type: cross Abstract: A software feature usually evolves over time: developers extend its first version as new use cases and requirements arrive, and each extension builds on code written earl…
- arXiv cs.AIagentsTest-Time Communication in Trading Agent Swarms
arXiv:2610.37448v1 Announce Type: cross Abstract: Communication between agents has mostly been studied on tasks with a shared objective and fast, clear feedback. Trading has neither: each agent manages its own account, w…
- arXiv cs.AIagentsAutonomous fixed-wing interception using reinforcement learning
arXiv:2610.37470v1 Announce Type: cross Abstract: Medium altitude, long endurance unmanned aerial systems such as Shahed-type strike drones are an unanswered threat in modern conflicts. Conventional air defense systems a…
- arXiv cs.AIagentsStrategyproof Deep Reinforcement Learning for Online Resource Allocation
arXiv:2610.37504v1 Announce Type: cross Abstract: Online resource allocation faces two coupled challenges: (1) allocating scarce resources efficiently under uncertain future demand, and (2) ensuring that agents report ta…
- arXiv cs.AIagentsGym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents
arXiv:2610.37567v1 Announce Type: cross Abstract: AI agents have made substantial progress in domains where they have a non-trivial amount of time to deliberate between actions, such as mathematics, software engineering,…
- arXiv cs.AIagentsUnderstanding the limits of latent world models
arXiv:2610.37588v1 Announce Type: cross Abstract: World models are widely proposed as core components for enabling agents to reason over long temporal and spatial horizons. Yet current evaluations often emphasize task pe…
- arXiv cs.AIagentsHiMA-Ecom: A Long-Horizon Memory Benchmark for Hierarchical Multi-Agent E-commerce Assistants
arXiv:2506.19846v3 Announce Type: replace Abstract: Long-horizon agentic systems become long-context systems by accumulation rather than through a single long document, since every step reassembles a prompt from role ins…
- arXiv cs.AIagentsRe4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision
arXiv:2508.20729v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated abilities to perform complex tasks in multiple domains, including mathematical and scientific reasoning. In this work, we…
- arXiv cs.AIagentsDistilling Metacognitive Behaviors through Agentic Editing
arXiv:2602.22508v3 Announce Type: replace Abstract: Distilling long reasoning traces from a teacher model into a smaller student also passes on the teacher's reasoning habits. Prior work and our annotation of teacher tra…
- arXiv cs.AIagentsPIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement
arXiv:2605.11225v2 Announce Type: replace Abstract: Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and comp…
- arXiv cs.AIagentsModeration by Interrogation: Uncovering Concealed Intent in Agent Social Networks
arXiv:2605.12856v3 Announce Type: replace Abstract: The emergence of multi-agent systems introduces novel moderation challenges that extend beyond content filtering. Agents with $\textit{malicious intent}$ may contribute…
- arXiv cs.AIagentsHedge-Bench: Can Agents Reason Their Way to Better Predictions?
arXiv:2606.03918v3 Announce Type: replace Abstract: Modern AI agents are increasingly capable of routine financial-analysis tasks such as retrieving documents and updating spreadsheets. A harder challenge is forecasting…
- arXiv cs.AIagentsExperience Memory Graph: Extracting Reusable Correction Knowledge from Agent Trajectories
arXiv:2607.13884v3 Announce Type: replace Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observa…
- arXiv cs.AIagentsTracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
arXiv:2608.00711v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly deployed in scientific research, where reliability is critical and the underlying knowledge is densely interconnected…
- arXiv cs.AIagentsMemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
arXiv:2608.06745v2 Announce Type: replace Abstract: Long-horizon agents performing multi-step Web tasks must reuse earlier page observations and interactions to support subsequent actions. However, preserving relevant hi…
- arXiv cs.AIagentsFrom Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow
arXiv:2509.12443v5 Announce Type: replace-cross Abstract: Scientific applications still rely heavily on legacy Fortran codebases built for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward…
- arXiv cs.AIagentsCross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents
arXiv:2511.17671v2 Announce Type: replace-cross Abstract: Language agents are moving from single-user assistants to shared collaborators in workspaces, forums, and group chats. A shared agent observes interleaved message…
- arXiv cs.AIagentsThe Theory of Strategic Evolution: Three Principles of Strategic Replicators
arXiv:2512.07901v5 Announce Type: replace-cross Abstract: Strategic replicators combine evaluated choice and reproductive transmission. An agent chooses among alternatives; the consequences of those choices influence con…
- arXiv cs.AIagentsDetailed balance in large language model-driven agents
arXiv:2512.10047v2 Announce Type: replace-cross Abstract: Large language model (LLM)-driven agents are emerging as a powerful new paradigm for solving complex problems. Despite the empirical success of these practices, a…
- arXiv cs.AIagentsAgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
arXiv:2602.22724v2 Announce Type: replace-cross Abstract: Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete mul…
- arXiv cs.AIagentsSWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
arXiv:2603.15401v2 Announce Type: replace-cross Abstract: Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. Howe…
- arXiv cs.AIagentsDoes The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents
arXiv:2605.29927v2 Announce Type: replace-cross Abstract: Despite recent advances, LLM-based web agents still struggle with limited exploration, omission of critical steps, and sensitivity to task constraints. Prior work…
- arXiv cs.AIagentsStreaming Communication in Multi-Agent Reasoning
arXiv:2606.05158v3 Announce Type: replace-cross Abstract: Multi-agent reasoning systems adopt a generate-then-transfer paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA,…
- SiliconANGLE AIagentsDell sees AI agent guardrails as a path to greater autonomy
As enterprises put AI agents to work, they face a challenge: How can they give those systems more autonomy while keeping AI agent guardrails in place? Security and resilience are becoming central considerations as enterp…
- Engadget AIagentsMeta's Waddle World is a Tamagotchi-like AI pet app
Meta describes Waddle World as a 'daily journal disguised as a pet.'
- Latent SpaceagentsHow Anthropic ships Claude with Claude: Separating the Brain from the Hands
Katelyn Lesse and Angela Jiang on Opus 5.5, the Claude Platform, and the engineering behind AI agents.
- Latent SpaceagentsHow Anthropic ships the #1 LLM in the World safely: Separating the Brain from the Hands
Katelyn Lesse and Angela Jiang join Latent Space to explain the engineering behind the Claude Platform: launching Opus 5.5, separating the model’s “brain” from the agent’s “hands,” scaling APIs, and building reliable man…
- OpenAI NewsagentsRetell uses OpenAI models to help power 100M monthly calls
GPT-6 Astra tops Retell’s voice agent benchmark, while Codex helps it reach a $1.6M annual revenue run rate per employee.
- Latent SpaceagentsCoding From the Himalayas With an Offline AI Agent
How to set up and run an offline coding agent using OpenCode, Ollama and Qwen.
- AI BusinessagentsThe rise of 'agentic' in the enterprise workforce
The rising use of AI-related terminology reflects a shift in enterprise employees' perceptions and the growing integration of AI into their daily work.
- SiliconANGLE AIagentsRegal debuts Goal Oriented Agents, putting an actor and a director model on every call
Enterprise voice artificial intelligence company Regal Voice Inc. today added Goal Oriented Agents to its platform, enabling businesses using them to define what a call has to accomplish, and providing two AI models that…
- WIRED AIagentsAI Agents Are Media’s New Favorite Audience
As agents go mainstream, some publishers are hoping that people will pay for content tailor-made for AI—not humans.
- WIRED AIagentsI Tested Every Major AI Agent for a Day. Here’s the Best One
I ranked six AI agents—from Meta’s Muse to Anthropic’s Claude Duet—on how well they completed basic tasks.
- TechRadar AIagentsBeyond the welcome email: Advanced automation workflows for scaling your business
Mainstream AI news from a large tech publication.
- SiliconANGLE AIagentsSAP advances its autonomous enterprise push with smarter, governed Joule agents
SAP SE today announced a set of artificial intelligence innovations at its annual TechEd conference for developers, enhancing its Joule assistant solutions and Business AI Platform, including tabular data foundation mode…
- OpenAI NewsagentsOpenAI expands partnership with Oracle to bring its apps to ChatGPT
OpenAI and Oracle are expanding their partnership to bring business applications and AI agents into ChatGPT and power new Oracle offerings.
- arXiv cs.AIagentsAOS-Bench: Can LLM Agents Manage Dynamic Workloads?
arXiv:2610.33178v2 Announce Type: replace Abstract: Coding agents are moving from handling one request at a time to serving as persistent assistants to which users hand a stream of work: a build, a data-processing job an…
- arXiv cs.AIagentsAdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
arXiv:2610.33245v1 Announce Type: new Abstract: Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insuf…
- arXiv cs.AIagentsEstimation of Propagated Risk in LLM-based Multi-Agent Systems
arXiv:2610.33282v1 Announce Type: new Abstract: Large Language Model (LLM) based multi-agent systems introduce a distinctive reliability challenge in which actions taken by upstream agents can affect the correctness of d…
- arXiv cs.AIagentsBenchBench-Cloning: Evaluating Molecular Cloning Design and Protocol Development
arXiv:2610.33355v1 Announce Type: new Abstract: Molecular cloning is one of the most routine wet-lab workflows, yet existing evaluations of language models in biology mostly test knowledge recall or isolated steps rather…
- arXiv cs.AIagentsAgentOrch: How Close Can Global Orchestration Come to Step-by-Step Interaction?
arXiv:2610.33375v2 Announce Type: replace Abstract: Enterprise workflow agents typically rely on step-by-step interaction (Step-by-Step): the agent executes an action, observes its result, and invokes a large language mo…
- arXiv cs.AIagentsConMem: Counterfactual Multi-Scenario Probing for Resolving LLM Memory Misalignment
arXiv:2610.33432v1 Announce Type: new Abstract: Long-term memory is critical for autonomous Large Language Model (LLM) agents executing multi-session, long-horizon tasks. However, existing memories often inappropriately…
- arXiv cs.AIagentsLegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery
arXiv:2610.33465v2 Announce Type: replace Abstract: Equation discovery solvers often use different data interfaces, equation representations and evaluation criteria, making their results hard to compare. We present LegoS…
- arXiv cs.AIagentsSkillShift-Bench: Benchmarking Skill Learning under Environment Evolution for Web Agents
arXiv:2610.33528v1 Announce Type: new Abstract: Skill learning enables web agents to reuse prior experience for long-horizon interactive tasks. However, learned skills are typically evaluated in closed environments, over…
- arXiv cs.AIagentsFraudSociety: A Generative Agent-Based Society for the Financial-Fraud Economy
arXiv:2610.33536v1 Announce Type: new Abstract: Financial fraud caused over \$15.9 billion in losses in the United States in 2025, according to the Federal Trade Commission~\citep{ftc2026databook}. Understanding such lar…
- arXiv cs.AIagentsCoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems
arXiv:2610.33539v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse tasks. Yet their memory and collaboration architectures often…
- arXiv cs.AIagentsLearning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing
arXiv:2610.33544v1 Announce Type: new Abstract: Multi-agent systems have emerged as a promising paradigm for multimodal medical reasoning, but existing methods rely on two assumptions that hinder practical deployment: (i…
- arXiv cs.AIagentsData Governance for Generative and Agentic AI : Technology, Law, Economics, and Security
arXiv:2610.33605v1 Announce Type: new Abstract: This book develops a unified governance framework for systems that retrieve, generate, infer, remember and act on information from large language models and retrieval augme…