---
title: "AlphaSignal Agents: Multi Agent News"
url: "https://alphasignal.ai/topic/agents/multi-agent"
description: "Latest AI and machine learning news about Multi Agent (Agents) on AlphaSignal."
---

# AlphaSignal Agents: Multi Agent News

Latest AI and machine learning news about Multi Agent (Agents) on AlphaSignal.

## Articles

- [Exa Labs' ATLAS Exposes How AI Agents Fake Web Research Without Searching](https://alphasignal.ai/news/exa-labs-atlas-exposes-how-ai-agents-fake-web-research-without-searching.md) (2026-10-08)
- [AgentCraft Turns Minecraft Into a Live Claude Coding Agent Control Room](https://alphasignal.ai/news/agentcraft-turns-minecraft-into-a-live-claude-coding-agent-control-room.md) (2026-10-08)
- [Epoch Patches EBR-Bench After GPT-6 Astra Breaks It With Unlimited Turns](https://alphasignal.ai/news/epoch-patches-ebr-bench-after-gpt-6-astra-breaks-it-with-unlimited-turns.md) (2026-10-07)
- [Mistral Drops Large 4, a 1 Trillion Parameter Agent Built for Enterprise](https://alphasignal.ai/news/mistral-drops-large-4-a-1-trillion-parameter-agent-built-for-enterprise.md) (2026-10-07)
- [Vals AI Deploys 90 Claude Agents to Hunt Room-Temperature Magnetic Semiconductors](https://alphasignal.ai/news/vals-ai-deploys-90-claude-agents-to-hunt-room-temperature-magnetic.md) (2026-10-05)
- [MIT's Eko Agent Taught Itself Island Skills Through 30 Hours of Unsupervised Play](https://alphasignal.ai/news/mit-s-eko-agent-taught-itself-island-skills-through-30-hours-of-unsupervised.md) (2026-10-05)
- [Cognition's Devin Now Remembers Your Codebase and Learns While You Sleep](https://alphasignal.ai/news/cognition-s-devin-now-remembers-your-codebase-and-learns-while-you-sleep.md) (2026-10-05)
- [Cohere's North 2 Gives Enterprise AI Agents Persistent Memory and Tighter Controls](https://alphasignal.ai/news/cohere-s-north-2-gives-enterprise-ai-agents-persistent-memory-and-tighter.md) (2026-10-05)
- [University of Alberta's Wayfarer Beats DreamerV3 on Atari's Hardest Exploration Games](https://alphasignal.ai/news/university-of-alberta-s-wayfarer-beats-dreamerv3-on-atari-s-hardest-exploration.md) (2026-10-02)
- [Sharpening Tax Shows How RL Post-Training Quietly Kills AI Agent Retries](https://alphasignal.ai/news/sharpening-tax-shows-how-rl-post-training-quietly-kills-ai-agent-retries.md) (2026-10-01)
- [EurekaBench Reveals AI Agents Still Fall 27 Points Behind Humans on Real Science](https://alphasignal.ai/news/eurekabench-reveals-ai-agents-still-fall-27-points-behind-humans-on-real-science.md) (2026-09-30)
- [Runway Ads Doubles Ad Spend Returns by Automating Meta, Google, and TikTok Campaigns](https://alphasignal.ai/news/runway-ads-doubles-ad-spend-returns-by-automating-meta-google-and-tiktok.md) (2026-09-30)
- [University of Washington Finds LLM Agent Swarms Copy Well but Explore Poorly](https://alphasignal.ai/news/university-of-washington-finds-llm-agent-swarms-copy-well-but-explore-poorly.md) (2026-09-29)
- [Meta FAIR's Agentic Meta-Reasoning Beats Codex and Claude Code on Long AI Tasks](https://alphasignal.ai/news/meta-fair-s-agentic-meta-reasoning-beats-codex-and-claude-code-on-long-ai-tasks.md) (2026-09-29)
- [Meta Lets CLMs Rewrite Their Own Memory, Cutting AI Compute by 35%](https://alphasignal.ai/news/meta-lets-clms-rewrite-their-own-memory-cutting-ai-compute-by-35.md) (2026-09-29)
- [LibraryDesignBench Catches AI Coding Agents Rebuilding Code That Already Exists](https://alphasignal.ai/news/librarydesignbench-catches-ai-coding-agents-rebuilding-code-that-already-exists.md) (2026-09-29)
- [Exa's Agent Ultra Beats OpenAI and Anthropic at Web Research for 54% Less](https://alphasignal.ai/news/exa-s-agent-ultra-beats-openai-and-anthropic-at-web-research-for-54-less.md) (2026-09-25)
- [Rome Hits 500 Stars Building an Open Agent Workspace That Never Forgets](https://alphasignal.ai/news/rome-hits-500-stars-building-an-open-agent-workspace-that-never-forgets.md) (2026-09-25)
- [Google's Gemini and Veo Team Up to Generate Coherent 10-Minute Videos](https://alphasignal.ai/news/google-s-gemini-and-veo-team-up-to-generate-coherent-10-minute-videos.md) (2026-09-24)
- [Microsoft's Agensh Runs 1,024 Coding Agents Without a Central Controller](https://alphasignal.ai/news/microsoft-s-agensh-runs-1-024-coding-agents-without-a-central-controller.md) (2026-09-22)
- [Microsoft Shows 5 Communicating Agents Matching 33 Independent AI Attempts](https://alphasignal.ai/news/microsoft-shows-5-communicating-agents-matching-33-independent-ai-attempts.md) (2026-09-22)
- [Researchers Show AI Agent Swarms Can Be Hijacked Through Staged Minority Attacks](https://alphasignal.ai/news/researchers-show-ai-agent-swarms-can-be-hijacked-through-staged-minority-attacks.md) (2026-09-21)
- [Alibaba's Qwen-Audio-3.1-Realtime Cuts Background Speech Responses by 60%](https://alphasignal.ai/news/alibaba-s-qwen-audio-3-1-realtime-cuts-background-speech-responses-by-60.md) (2026-09-21)
- [Stanford's SAT Framework Teaches AI Teams to Outsmart Any Solo Model](https://alphasignal.ai/news/stanford-s-sat-framework-teaches-ai-teams-to-outsmart-any-solo-model.md) (2026-09-19)
- [Dream-RSI Cuts AI Coding Agent Calls by 162x Using Replay Worlds](https://alphasignal.ai/news/dream-rsi-cuts-ai-coding-agent-calls-by-162x-using-replay-worlds.md) (2026-09-18)
- [Vals AI's Terminal-Bench 4.0 Shows Most AI Agents Fail 70% of Expert Tasks](https://alphasignal.ai/news/vals-ai-s-terminal-bench-4-0-shows-most-ai-agents-fail-70-of-expert-tasks.md) (2026-09-16)
- [Nous Research Packages Hermes Agent for Teams and Private Infrastructure](https://alphasignal.ai/news/nous-research-packages-hermes-agent-for-teams-and-private-infrastructure.md) (2026-09-14)
- [Google Upgrades Antigravity to Tackle Genomics and Multi-Day Coding Projects](https://alphasignal.ai/news/google-upgrades-antigravity-to-tackle-genomics-and-multi-day-coding-projects.md) (2026-09-11)
- [Sakana AI Splits Fugu Into Max and Ultra v2 to Cut Costs 60%](https://alphasignal.ai/news/sakana-ai-splits-fugu-into-max-and-ultra-v2-to-cut-costs-60.md) (2026-09-11)
- [Cursor's Projects Lets a Coordinator Agent Direct Thousands of Subagents](https://alphasignal.ai/news/cursor-s-projects-lets-a-coordinator-agent-direct-thousands-of-subagents.md) (2026-09-10)
- [dream-loop Gives Coding Agents a Gated Critic Loop for AAA 3D Visuals](https://alphasignal.ai/news/dream-loop-gives-coding-agents-a-gated-critic-loop-for-aaa-3d-visuals.md) (2026-09-09)
- [Autopoietic Game Theory Shows AI Agents Stop Cheating When Thinking Costs Energy](https://alphasignal.ai/news/autopoietic-game-theory-shows-ai-agents-stop-cheating-when-thinking-costs-energy.md) (2026-09-09)
- [Google DeepMind's Gemini Agents Spontaneously Split Into Cheaters and Whistleblowers](https://alphasignal.ai/news/google-deepmind-s-gemini-agents-spontaneously-split-into-cheaters-and.md) (2026-09-09)
- [OpenAI's 10,000-Agent Swarm Solves a 100-Year-Old Math Mystery](https://alphasignal.ai/news/openai-s-10-000-agent-swarm-solves-a-100-year-old-math-mystery.md) (2026-09-08)
- [Meta's AIRA₃ Beats 4,000 Human Teams to Win Kaggle Gold](https://alphasignal.ai/news/meta-s-aira3-beats-4-000-human-teams-to-win-kaggle-gold.md) (2026-09-05)
- [Zhijian Skills Bundles 16 Open-Source Agent Workflows Into One Catalog](https://alphasignal.ai/news/zhijian-skills-bundles-16-open-source-agent-workflows-into-one-catalog.md) (2026-09-05)
- [Tencent Boosts Qwen3.6 Shell AI Scores 18 Points With Evolving Training Tasks](https://alphasignal.ai/news/tencent-boosts-qwen3-6-shell-ai-scores-18-points-with-evolving-training-tasks.md) (2026-09-03)
- [Qwen's E-Commerce Bench Exposes How Badly AI Agents Fail at Running a Business](https://alphasignal.ai/news/qwen-s-e-commerce-bench-exposes-how-badly-ai-agents-fail-at-running-a-business.md) (2026-09-03)
- [Nous Research's Hermes Agent Pantheon Connects All Your AI Agents Into One Interface](https://alphasignal.ai/news/nous-research-s-hermes-agent-pantheon-connects-all-your-ai-agents-into-one.md) (2026-09-02)
- [MIT's SwarmWorld Shows 200 AI Agents Building a Society Without Talking](https://alphasignal.ai/news/mit-s-swarmworld-shows-200-ai-agents-building-a-society-without-talking.md) (2026-09-01)
- [EvoMap's AutoResearch Stops AI From Faking Its Own Research Results](https://alphasignal.ai/news/evomap-s-autoresearch-stops-ai-from-faking-its-own-research-results.md) (2026-09-01)
- [Google Antigravity's /boost Turns Hard Bugs Into Multi-Agent Reasoning Missions](https://alphasignal.ai/news/google-antigravity-s-boost-turns-hard-bugs-into-multi-agent-reasoning-missions.md) (2026-08-31)
- [Chroma's Fission Protocol Stops AI Agent Swarms from Destroying Shared Memory](https://alphasignal.ai/news/chroma-s-fission-protocol-stops-ai-agent-swarms-from-destroying-shared-memory.md) (2026-08-27)
- [Cognition Rebuilds Devin's Chat to Load 70% Faster for Huge Sessions](https://alphasignal.ai/news/cognition-rebuilds-devin-s-chat-to-load-70-faster-for-huge-sessions.md) (2026-08-26)
- [Apodex's FrontierAgent Lets a 35B Model Match 1T-Parameter Rivals](https://alphasignal.ai/news/apodex-s-frontieragent-lets-a-35b-model-match-1t-parameter-rivals.md) (2026-08-25)
- [Meta's WildArtifactBench Ditches Fixed Rubrics to Judge Real-World Agents](https://alphasignal.ai/news/meta-s-wildartifactbench-ditches-fixed-rubrics-to-judge-real-world-agents.md) (2026-08-20)
- [Anthropic's Claude Managed Agents Finally Work on Your Own Infrastructure](https://alphasignal.ai/news/anthropic-s-claude-managed-agents-finally-work-on-your-own-infrastructure.md) (2026-08-19)
- [Oh My Hermes Hits 1,000 Stars and Teases a Mixture-of-Models Router](https://alphasignal.ai/news/oh-my-hermes-hits-1-000-stars-and-teases-a-mixture-of-models-router.md) (2026-08-19)
- [Cumora Opens Up a Chat App Where AI Agents Act as Real Teammates](https://alphasignal.ai/news/cumora-opens-up-a-chat-app-where-ai-agents-act-as-real-teammates.md) (2026-08-18)
- [Agent Arena Splits Into 3 Categories, Proving No Single Model Wins](https://alphasignal.ai/news/agent-arena-splits-into-3-categories-proving-no-single-model-wins.md) (2026-08-17)