arXiv论文：SOP与上下文知识分离管理，智能体技能等效率从12%提升至58%
Separation of Skilling Context for Standard Operating Procedure-based Agents
做企业流程自动化的人可以看这篇：它把SOP文档和隐含知识分开管理，让智能体在SOP更新后不用每次重新人工调试。8个Indeed工作流上等效率从12%拉到58%，对比明显，写agent框架的值得借鉴这个思路。
arXiv 论文提出 SOP-skill drift 问题：LLM 智能体从标准操作规程（SOP）生成可执行技能时，因 SOP 为人类可读而省略隐含知识，自动化缺口需人工反复填补。论文方法是将 SOP 与上下文知识（Contextual Knowledge, CK）分开管理，并引入 contract-aware 评估，区分真正的违规与可由 CK 解决的差异。
在 8 个来自 Indeed 的工作流上（单 LLM 设置），该方法的函数等效率从 12% 提升至 58%。在 3 种 SOP 修订扰动实验中，先前提取的 CK 已覆盖 79.5% 的新增自动化缺口，说明 CK 能随 SOP 演化持续复用，减少重复人工干预。
这篇论文面向做企业流程自动化的开发者：把流程文档的知识抽取为独立可维护的 CK 层，比每次 SOP 更新后重训或重写技能更省成本。
Separation of Skilling Context for Standard Operating Procedure-based Agents
Standard Operating Procedures (SOPs) are kept concise for human readability, so LLM agents that generate executable skills from them lack the tacit knowledge and implementation details needed for automation. Human intervention fills these gaps, but must be repeated as SOPs evolve---a problem we call \textit{SOP-skill drift}. We propose managing SOPs and Contextual Knowledge (CK) separately, together with a \textit{contract-aware} evaluation that distinguishes genuine violations from CK-resolved differences. On eight Indeed-derived workflows (single LLM), it raises the functional-equivalence rate from 12\% to 58\%. Under three SOP-revision perturbations, previously extracted CK already covers 79.5\% of newly introduced automation gaps.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include 智能体, SOP, LLM, paper.
Source attribution: curated from arXiv cs.AI (@Mitsuhiro Nakayama, Toshiaki Sota, Takehiko Yamaguchi, Michiaki Tatsubori).
