longcat-flash-prover

【开发与工程】Integrate agentic tool interaction (Lean4 compiler, syntax checkers) with curriculum-based RL for formal reasoning. Replace standard importance sampling with Hierarchical Importance Sampling Policy Optimization (HisPO): sequence-level masking removes train-inference discrepancies, token-level masking filters inconsistent tokens, staleness control man…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准