- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes HFC-GRPO, which gives non-zero advantages to all-correct and all-wrong groups in GRPO using a historical predicts, while leaving mixed groups unchanged. Experiments on math reasoning and search-agent tasks show improvements over GRPO and other baselines.
Critical strengths
The idea of restoring signed advantages only on homogeneous groups, while keeping mixed-group GRPO exactly intact, is simple and well-motivated. The evaluation covers a broad range of settings.
Critical weaknesses
The notation is hard to follow; there are some unnecessary notations (For example, L173, βπ‘ β [πβ, 1 β πβ], with πβ = 0.02, it does not need πβ.). In addition, the main paper does not define the RL-ZVP and GRPO-DBB protocols or the ID/OOD split, and all main results and ablations use Qwen3-8B. Moreover, the method targets homogeneous groups, but these are only 21β31% of groups in the main runs, where GRPO already trains reasonably well. Settings dominated by homogeneous groups should be tested to verify their methods. The gain also seems small relative to the added complexity (For example, NGRPO is a very simple method compared to their method). Finally, this is not the official format for ICLR 2027.
Questions for authors
Please see Weaknesses.