aiIMAGE
小米 MiMo-V2.6 公开最大规模 RL 扩展实验
小米 MiMo 公开迄今最大规模强化学习扩展训练，并发布技术报告，讲算力、环境与评分体系如何同步扩展。
alphaXiv
@askalphaxiv2026.09.24收录原推发布于 2026.09.22
alphaXiv @askalphaxiv原推发布于 2026.09.22
“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
x.com/askalphaxiv/status/2102263712472342718采集于 2026.09.24 01:48