i-grpo-self-feedback-reasoning

【效率与协作】Improve LLM reasoning through iterative refinement where the model refines its best previous attempts. Two-stage training: exploratory draft generation, then conditioned refinement using GRPO. Dynamic conditioning signals evolve with policy, enabling state-of-the-art math reasoning on AIME (85.62%).

独立 GitHub 快照 · 自动分类 · 以原作者文档为准