Xiaomi's GAGAR: quality-aware advantage redistribution improves code agent RL

XiaomiMiMo · hf · 2026-09-29

Xiaomi's MiMo team introduces GAGAR, a framework fixing a core GRPO weakness in code-agent RL: all test-passing trajectories in a group get identical advantages, ignoring implementation quality.

Method

Results

Conclusion: combining test-based verification with groupwise agentic grading improves quality and stability of code agent RL.

Original post →

More from coding & agent

coding & agent channel →