註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Xiaomi MiMo Developers
@XiaomiMiMoDevs
加入 June 2026
1 正在關注    3.4K 粉絲
🛠️ MiMo-V2.6 update: tool-call repetition, diagnosed & fixed. After the MiMo-V2.6 series models launched, we noticed them sometimes repeating identical or highly similar tool calls — burning context and stalling tasks, especially in MiMo Desktop, MiMo Code and OpenCode. Root cause A "reward blind spot" in scaling RL: when rewards only track final-answer correctness, inefficient behaviors along the way go unnoticed — and get amplified as training scales. Concretely, our flooding penalty only kicked in at >32 tool calls per turn, so anything below that threshold went completely unpunished. The fix We trained a light-weight repetition-specialized RL teacher — just 12 steps, ~7k examples — and merged it into the main model via MOPD, at roughly 4% of the cost of a full mixRL retrain. Repetition dropped sharply across harnesses and context lengths, while benchmarks held steady. 📦 Updated models, open-sourced (MOPD suffix): 📝 Full postmortem: Huge thanks to our community for the patience and feedback 🙏 Updated models go live on our API platform Sep 25, 06:00 (UTC+8), names unchanged. And for MiMo Desktop users: everyone's remaining quota in the current window will be reset.
顯示更多
0
69
1.2K
83
轉發到社區