thor-tool-hierarchical-optimization-rl

【数据与研究】Train LLMs for tool-integrated mathematical reasoning via hierarchical RL combining episode-level problem correctness with step-level code execution quality. Addresses sparse rewards in reasoning chains through TIRGen data construction and self-correcting inference with dynamic backtracking.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准