计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
search-r2-refinement-rl【效率与协作】Decompose search-integrated reasoning into actor (generates trajectories) and refiner (identifies and corrects flawed steps). Refiner performs surgical cut-and-regenerate correction preserving valid prefixes. Trained end-to-end with GRPO; adds minimal overhead (2%) to baseline.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准