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。
attnrl-attention-compass-reasoning-exploration【效率与协作】Guide LLM exploration in reasoning tasks using attention patterns as navigation signals. This technique branches exploration from high-attention tokens (likely reasoning steps) and applies adaptive sampling to maintain effective gradients, significantly improving training efficiency for mathematical reasoning.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准