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。
uniqueness-aware-rl【效率与协作】Improves LLM reasoning by rewarding correct solutions that exhibit rare high-level strategies, preventing exploration collapse and discovering more diverse solution approaches across mathematics, physics, and medical reasoning.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准