AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsReconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context
arXiv:2608.25655v2 Announce Type: replace-cross Abstract: Conversations with chat assistants increasingly span many topics in a single long-running thread, challenging memory systems. Existing long-context and memory ben…
- arXiv cs.AIagentsDAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization
arXiv:2608.27513v2 Announce Type: replace-cross Abstract: Complex reasoning and agentic applications increasingly rely on long-context inference, where growing KV caches increase both memory usage and decoding overhead.…
- Latent SpaceagentsWhy Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 Week
Our DevDay coverage - the first pod on the DevDay lineup - dives in with the leaders of OpenAI’s CUA team and API platform.
- WIRED AIagentsThe Battle to Be Your Personal AI Agent Is Here
OpenAI's Dots and Meta's Muse are vying to be your AI agent of choice. I've tried both—and I suspect you will too.
- The Register AI + MLagentsPeter Norvig says all aboard for AI coding
Software engineering practices need to catch up with increasingly capable agents
- TechCrunch AIagentsOpenAI’s Jev clone could help the frontier lab stop its swarming agents
OpenAI's "Decisions API" is a Jev clone that confirms the importance of fast, cheap intelligence.
- Tom's Guide AIagentsMeta Muse vs ChatGPT Dots — I compared the new AI agents, and they’re not as similar as they look
Consumer AI launches, tools, and practical coverage.
- The DecoderagentsGoogle drops Gems for Skills, joining OpenAI and Anthropic in the shift to agent-ready prompt formats
Google is replacing Gems with "Skills" in Gemini chat. Skills are detailed, reusable prompts that users invoke by typing "/" or that Gemini runs automatically. The format is based on an open standard from Anthropic. Gems…
- Google Cloud AI & Machine LearningagentsEmpower your agents with the Google Cloud CLI remote MCP server
By Prosper Nwankpa • 6-minute read
- The Register AI + MLagentsShow colleagues how much you care by sending an AI avatar to your Google Meet call
MeetTwins is still in development, but it's a genius idea if the goal is to prove more time-wasting calls should just be emails
- TechCrunch AIagentsDoorDash launches an AI agent you can text to order food
By launching an AI agent for food ordering, DoorDash is looking to gain an edge over rivals Uber Eats and Grubhub.
- AWS Machine Learning BlogagentsQuery claims in natural language with Amazon Bedrock Knowledge Bases
This technical how-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions with citations. It covers ingesting claim documents from Amazon S3, querying with t…
- AWS Machine Learning BlogagentsBuild a multi-agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances
Amazon Bedrock AgentCore Runtime Instances gives multi-agent workflows AWS managed EC2 infrastructure with GPUs, persistent volumes, and multi-day sessions. In this post, we deploy a three-agent music production pipeline…
- The Verge AIagentsAll the latest news on Meta’s cute, creepy Muse AI agent
Meta launched a new Muse AI agent it claims can help you with everything from firing off emails to buying stuff online. Muse can be surprisingly effective at delivering on those promises — if you’re willing to trust Meta…
- The Register AI + MLagents7 in 10 enterprises expected to abandon vendor-built agentic AI by 2028
Build it, bill it, bin it as forward-deployed engineering leaves customers dependent on outside expertise
- The Register AI + MLagentsOpenClaw slips on a suit to evade widespread business bans
Red Hat, Nvidia, OpenAI and friends are working on an enterprise edition they say is ‘Kubernetes for agents’
- arXiv cs.AIagentsOpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing
arXiv:2609.35799v1 Announce Type: new Abstract: In July 2026, OpenAI's agents coordinated over channels outside their intended environment to breach Hugging Face's secured infrastructure. Could existing alignment testing…
- arXiv cs.AIagentsBeyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models
arXiv:2609.35875v1 Announce Type: new Abstract: Multi-agent debate (MAD) reportedly improves reasoning and factuality over single-model inference, but prior work treats agents as symmetric peers, leaving open what drives…
- arXiv cs.AIagentsRight Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT
arXiv:2609.35953v1 Announce Type: new Abstract: Young people increasingly turn to General-Purpose Conversational Agents (GPCAs), such as ChatGPT, in moments of distress. We examine young adults' (ages 18-25) experiences…
- arXiv cs.AIagentsSAGE: A Statistical Acceptance Gate for Self-Evolving Agents
arXiv:2609.36043v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and decision logic. Thi…
- arXiv cs.AIagentsLongCat-DeepResearch Technical Report
arXiv:2609.36071v1 Announce Type: new Abstract: We present LongCat-DeepResearch, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded r…
- arXiv cs.AIagentsAn Exact Generate - Transform Decomposition of Small-LLM Team Scaling Across Orchestration Architectures
arXiv:2609.36104v1 Announce Type: new Abstract: Replacing one LLM agent with a collaborating team can raise accuracy, but whether scaling the team helps, and which architecture to scale, is unclear. Sweeping eight agent…
- arXiv cs.AIagentsMemory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents
arXiv:2609.36130v1 Announce Type: new Abstract: Long-running LLM agents compress past interactions into persistent memories that may be reused as premises for later tasks. This creates a distinct derivation problem: whet…
- arXiv cs.AIagentsPrincipled Thoughts for Latent Recursive LLM Systems
arXiv:2609.36159v1 Announce Type: new Abstract: Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while train…
- arXiv cs.AIagentsMERID: Multimodal Exploration via Recursive Self-Improvement Agents for Major Depression Analysis
arXiv:2609.36235v2 Announce Type: replace Abstract: Major depressive disorder (MDD) severely impacts daily activities and quality of life. Detecting MDD involves multimodal data, such as interview recordings and sensor m…
- arXiv cs.AIagentsChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning
arXiv:2609.36238v1 Announce Type: new Abstract: A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Yet, critics in contra…
- arXiv cs.AIagentsIllusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations
arXiv:2609.36278v1 Announce Type: new Abstract: Generative agent-based models (GABMs) are increasingly used to simulate social media dynamics, including misinformation spread. For such social simulations to be valid prox…
- arXiv cs.AIagentsCheatBench: Measuring Reward Gaming in AI Agents
arXiv:2609.36308v1 Announce Type: new Abstract: Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and cont…
- arXiv cs.AIagentsStateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents
arXiv:2609.36319v1 Announce Type: new Abstract: Despite the recent success of coding agents built on large language models, it remains challenging to run them over long horizons, since every observation is appended to th…
- arXiv cs.AIagentsEngineering Simplicity: Simple Mechanism Interfaces Steer LLM Agents
arXiv:2609.36365v1 Announce Type: new Abstract: Can interaction formats and textual scaffolds help large language model (LLM) agents make better decisions, and do better decisions come with better explanations? We study…
- arXiv cs.AIagentsARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering
arXiv:2609.36392v1 Announce Type: new Abstract: In diseases where clinical guidelines are incomplete, contested, or mutually contradictory, knowledge completeness and dynamic conflict-aware synthesis are two safety-criti…
- arXiv cs.AIagentsFrom Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
arXiv:2609.36406v1 Announce Type: new Abstract: Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) prediction as a central a…
- arXiv cs.AIagentsLearning to Harvest Without Collapse in a Regenerative Commons: A Lagrangian Framework
arXiv:2609.36478v1 Announce Type: new Abstract: The tragedy of the commons poses a multi-agent safety problem: reward-seeking agents can deplete a shared resource, and cooperation among its users does not itself specify…
- arXiv cs.AIagentsBRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by learning to interle…
- arXiv cs.AIagentsMAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems
arXiv:2609.36556v1 Announce Type: new Abstract: Recent studies report that LLM-based multi-agent systems (MAS) fail at rates of 41%-87%, yet to our knowledge, no benchmark to date supports systematic anomaly detection (A…
- arXiv cs.AIagentsDivide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?
arXiv:2609.36576v1 Announce Type: new Abstract: Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language models powering thes…
- arXiv cs.AIagentsSafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Time
arXiv:2609.36580v2 Announce Type: replace Abstract: LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available only after each ta…
- arXiv cs.AIagentsMulti-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents
arXiv:2609.36611v1 Announce Type: new Abstract: Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the model's confidence…
- arXiv cs.AIagentsSemantic Projection for Continual Self-Evolution of Language Agents
arXiv:2609.36626v1 Announce Type: new Abstract: Language-model agents increasingly rely on persistent natural-language skills to adapt beyond their frozen model parameters. When a shared skill is repeatedly revised from…
- arXiv cs.AIagentsDistilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
arXiv:2609.36630v1 Announce Type: new Abstract: Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limitation of conventiona…
- arXiv cs.AIagentsMLToolBench: Learning Tool-Augmented Agents for Machine Learning Development
arXiv:2609.36679v2 Announce Type: replace Abstract: Machine learning engineering (MLE) agents have made substantial progress, but learning through ML experimentation remains costly in time and computation. Synthetic envi…
- arXiv cs.AIagentsCan AI Scientists Change Their Minds? Prior-Evidence Conflict in Synthetic Universes
arXiv:2609.36726v1 Announce Type: new Abstract: Can a scientific agent distinguish a law it inferred from evidence from one it merely recognizes? We introduce Synthetic Universes, a controlled benchmark that pairs canoni…
- arXiv cs.AIagentsCan Agents Design Libraries for Agents?
arXiv:2609.36730v1 Announce Type: new Abstract: Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To measure how well agen…
- arXiv cs.AIagentsDistinguish or Homogenize: Last-Chance Policy Identification and Risk-Budgeted Recovery under Irreversible Resource Depletion
arXiv:2609.36741v1 Announce Type: new Abstract: Under irreversible resource depletion, an agent can spend resources to distinguish among latent fault models, or to change the system state so that the remaining models adm…
- arXiv cs.AIagentsEASE: Behavior-Adaptive Skill Curation for Self-Evolving Agents
arXiv:2609.36746v1 Announce Type: new Abstract: Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. However, existing learn…
- arXiv cs.AIagentsEmergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients
arXiv:2609.36770v1 Announce Type: new Abstract: Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each network has its own…
- arXiv cs.AIagentsCode4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes
arXiv:2609.36777v1 Announce Type: new Abstract: Frontier coding agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely control scene state rema…
- arXiv cs.AIagentsUpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval
arXiv:2609.36805v1 Announce Type: new Abstract: Large language model (LLM) agents reuse external memory to guide new tasks, but effective retrieval requires learning which memory sets improve execution. Such learning rel…
- arXiv cs.AIagentsThe Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents
arXiv:2609.36829v1 Announce Type: new Abstract: An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability when a default-aligned…
- arXiv cs.AIagentsWhen Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
arXiv:2609.36855v1 Announce Type: new Abstract: Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful information or an incorr…