We are sharing this progress report at booth 260 poster in Hall3 of the IClR venue now.

This is for you AI at Meta

📣 New Discovery on Computer Use Agent With just 312 high-quality trajectories + open-source model, we've surpassed Claude 3.7 Sonnet (thinking) in computer use capabilities 🚀 ⚡️ In the new era of AI Agent training, many key questions remain: • Can open-source models + small

312 quality trajectories + open-source model beats Claude 3.7 Sonnet (thinking) in computer use 🚀 We answer the following important questions in our recent tech report: github.com/GAIR-NLP/PC-Ag… 1. Can open-source models + small high-quality datasets outperform top closed-source

The real breakthrough isn't better AI—it's breaking free from nature's constraints We're witnessing a paradigm shift from "passive adaptation" to "active construction" in AI training. 🌊 The old way: AI learns from whatever data naturally exists • Constrained by existing

nice discussion

What foundation models do we REALLY need for the RL era? And what pre-training data? Excited to share our work: OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling arxiv.org/pdf/2506.20512 ✨ Key breakthroughs: - First RL-focused mid-training approach - Llama

Tech history: Every time humanity hits a tech wall, we just wait for someone named Ilya to show up and save the world :) - Neural nets stuck? - Language models plateau? - ... (skip tons of stuff) - ... - Superintelligence coming?

FacTool has been accepted to COLM 2025 - two years after its arXiv debut! While the landscape of LLMs has changed a lot since then, tool-augmented LLMs and RAG are still among the most effective and practical approaches for detecting / mitigating hallucinations (ref:

RepoST was accepted to Conference on Language Modeling !!! See you in Montreal 🚀 #COLM2025

We can finally share UI-TARS-2🥳🥳 — a native GUI agent trained with multi-turn agent RL ⚡️⚡️Key highlights (all-in-one model!): 💻Computer Use: 47.5 OSWorld · 50.6 WindowsAgentArena 📱Phone Use: 73.3 AndroidWorld 🛜Browser Use: 88.2% Online-Mind2Web 🎮Gameplay: ~60% human