Very cool work from Meta Superintelligence Lab. They are open-sourcing Meta Agents Research Environments (ARE), the platform they use to create and scale agent environments. Great resource to stress-test agents in environments closer to real apps. Read on for more:

🏗️ ARE: scaling up agent environments and evaluations In the LLM+RL era, evals and envs are the bottleneck Happy to release Gaia2, an extensible benchmark for agents aiming to reduce the sim2real gap + ARE, the platform in which Gaia2 is built Enjoy evaluating your agents! 👇

Did you see that the Agent Research Environment is MCP compatible? -> using any MCP tools with any agent is now completely trivial! Check it out! We've used an LLM agent to 1) move a robot arm remotely 2) depending on real time web search results! :D How to in thread ^^

🧠Great research from Meta Superintelligence Labs. Proposes Meta Agents Research Environments (ARE) for scaling up agent environments and evaluations. ARE lets researchers build realistic agent environments, run agents asynchronously, and verify them cleanly. On top of it

We released Gaia2 and ARE, our platform for agent environments and evals in the LLM+RL era! This was such a fun project to work on, I hope you like it too :) Paper: arxiv.org/abs/2509.17158 Demo Hugging Face: huggingface.co/spaces/meta-ag… Blog post: huggingface.co/blog/gaia2

merci la dream team ✨🫶 Grégoire Mialon Romain Froger Dheeraj Mekala Amine Benhalloum ✈️ NeurIPS Pierre, Maxime, Ulyana Piterbarg, Thomas Scialom and everyone else!

We need better agent evaluations! Glad to have collaborated with Meta Super Intelligence Lab to release Gaia2 and ARE! GPT5 (high) from OpenAI is leading on execution, search, ambiguity, adaptability and noise. Kimi-K2 from Kimi.ai is leading open weight. Full

(🧵) Today, we release Meta Code World Model (CWM), a 32-billion-parameter dense LLM that enables novel research on improving code generation through agentic reasoning and planning with world models. ai.meta.com/research/publi…

Two years ago, I had the privilege of collaborating with Thomas Scialom and Grégoire Mialon at @MetaAI on GAIA, one of the first agentic benchmarks, designed to measure progress towards useful-in-the-real-world AGI. This week, the team launched Gaia2, built inside their new

Thrilled to see @MetaAI launch 𝗚𝗮𝗶𝗮𝟮, built inside their new 𝗔𝗴𝗲𝗻𝘁 𝗥𝗟 𝗘𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁 platform! 🚀 Proud that Surge AI helped contribute — just as we did with GAIA two years ago. A quick story 🧵

Read the ARE & GAIA2 paper from AI at Meta by Grégoire Mialon, Romain Froger, Amine Benhalloum and Thomas Scialom Very very interesting eval setup! Basically what they do is that they created the updated GAIA2 using a specific pattern of setup, and ARE (Agents Research

We released ARE and Gaia2 one week ago, time to share some observations and add new models to the leaderboard! huggingface.co/blog/meta-agen…

Welcome Nex-N1, a new series of agentic foundational models, to Hugging Face - available in different sizes from 8B, 30B, 32B to 671B - strong in tool-use, web-search and real-world agentic workflow - some SFT dataset has been open sourced Technical report come up soon!

I am at #NeurIPS2025! I am hiring an intern for our Paris team to succeed Dheeraj Mekala and Ulyana Piterbarg, DM if you want to work on what's next for agents Will also have a look back on Gaia and introduce Gaia2 at the Scaling Environments for Agents workshop on Sunday!

I'll be NeurIPS Conference in San Diego this week, together with the co-authors of ARE/Gaia2 Grégoire Mialon & Amine Benhalloum . Would love to connect: let’s talk about what’s next for agents!

// THE CASE FOR ENVIRONMENT SCALING // Environment scaling may be as important as model scaling for agentic AI. Current AI research suggests that building a powerful agentic AI model isn't just about better reasoning. It's also about better environments. The default approach

Great to see Gaia2 being adopted by the community as a frontier eval! 😄 At #NeurIPS2025, we were so pleased to meet so many people building on top of ARE!