自动从交互日志构建可执行技能，提升智能体任务复现一致性。
Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
- 将技能分解为流程、语义和运行附件三部分，捕捉控制流与安全机制。
- 在70个技能上实验，任务复现一致率比基线提升10.5%。
- 适合需要高可靠性任务执行的智能体系统研发人员。
大型语言模型智能体日益依赖技能来编码过程知识，但高质量技能仍需人工编写，成本高昂。本文研究从异构交互证据（包括示范、智能体轨迹、工具调用记录和执行日志）中自动构建技能。我们指出，从日志生成技能并非简单摘要任务，因为日志碎片化、冗余，且可能遗漏罕见但关键安全行为。为此，提出RWSA：一种面向工作流的中间表示，将技能分解为流程结构、执行语义和运行时附件，以捕捉任务分解、控制流、验证、安全、回滚与状态管理。基于RWSA，提出W2S框架：对日志进行分段，生成局部技能草稿，对齐共享结构，调和分支差异，并压缩冗余，同时保留证据与置信度标注。在70个技能上的实验表明，W2S相比摘要与提示基线，行为复现一致性提升10.5%，凸显应将日志视为可执行的运行时规范而非可压缩文本。
原文摘要 · Abstract (English)
Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write. This paper studies automatic Skill construction from heterogeneous interaction evidence, including demonstrations, agent trajectories, tool traces, and execution logs. We argue that trace-to-skill construction is not simple summarization tasks, because traces are fragmented, redundant, and may miss rare but safety-critical behaviors. To address this, we introduce RWSA, a workflow-oriented intermediate representation that decomposes Skills into Workflow structure, execution Semantics, and runtime Attachments, capturing task decomposition, control flow, verification, safety, rollback, and state management. Building on RWSA, we propose W2S, a framework that segments traces, induces local Skill drafts, aligns shared structures, reconciles branches, and compresses redundancy while preserving evidence and confidence annotations. Experiments on 70 Skills show that W2S improves behavioral replay consistency by 10.5% over summarization- and prompting-based baselines, highlighting the need to treat traces as executable runtime specifications rather than compressible text.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。