From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents

论文提出把低层 atomic actions 迭代沉淀为 Standard Operating Procedures 的路线。系统从 agent 轨迹中识别重复子流程，把稳定操作抽象成可复用 SOP，再通过执行反馈修订这些流程。它把 self-evolving agent 的学习对象落在“可执行流程资产”上，比单纯记忆过去对话更适合减少重复工具调用和步骤漂移。