Xiaomi fixes MiMo-V2.6 tool-call repetition: an RL reward blind spot, patched at 4% of retrain cost

udmrzn · x · 2026-09-28

Xiaomi's MiMo team diagnosed and fixed tool-call repetition in MiMo-V2.6, which burned context and stalled tasks in MiMo Desktop, MiMo Code and OpenCode. Root cause: an RL "reward blind spot" — rewards only tracked final-answer correctness, and the flooding penalty only kicked in above 32 tool calls per turn, so sub-threshold repetition went unpunished and scaled with training.

The fix: a lightweight repetition-specialized RL teacher (12 steps, 7k examples) merged into the main model via MOPD at 4% of a full mixRL retrain cost. Repetition dropped sharply across harnesses and context lengths while benchmarks held steady.

Original post →

More from Models

Models channel →