Xiaomi MiMo-V2.6: largest RL scaling run to date, published openly

alphaXiv @askalphaxivOriginally posted 2026.09.22

Open original on X

“MiMo-V2.6 Scaling Reinforcement Learning Towards Self-Improvement” Xiaomi MiMo just completed their largest RL scaling run so far, openly. And it came along with a technical report, outlining how they've scaled RL across compute, environments, and grading. tl;dr The run https://t.co/9QeMsdjJyf