RL training stability tricks: prompt-mean loss, asymmetric clipping and entropy-adaptive GRPO

tokenbender · x · 2026-09-22

The author breaks down key RL training modifications: sticking with GRPO rather than fancier algorithms but tuning it for stability and scale — prompt-mean loss over token-mean loss to stop long answers from getting excess gradient weight (DAPO); separate clipping bounds for positive/negative advantages (DAPO); entropy-adaptive clipping (mai-thinking-1); and segment-level credit shaping (TreeAdv).

They also note that 13% policy-drift staleness with large throughput implies the chosen environments run or improve directly on base weights without any curriculum — otherwise training would have suffered penalties.

Related event: Xiaomi MiMo's 1M-Context RL Training Details Spark Debate(13 posts)→

Original post →

More from Models

Models channel →