这篇论文提出了WML方法，能精准定位Agent工作流失败节点并复用外部技能知识，在SpreadsheetBench和Compiler-Supported50上表现亮眼，比直接SkillAgent省不少token。
WML方法通过Node--Mechanism Attribution识别失败工作流节点、原因机制及最小编辑目标，将单机制缺陷路由到L3资源，跨机制缺陷路由到L2协议。在SpreadsheetBench上，WML使用DeepSeek达到90.33±1.53 Hard Accuracy，使用Qwen3.6-Flash达到74.67±3.51。无额外优化时，学到的技能迁移到WikiTableQuestions取得84.00±2.00和83.00±2.00 Denotation Accuracy。在Compiler-Supported50上，WML同时取得最高hard-PASS率和最低每次成功任务成本，编译执行相比直接SkillAgent大幅减少token和调用次数。代码和工件已开源在GitHub。
Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills
Agent Skills package reusable procedural knowledge as external artifacts for frozen language-model agents, yet existing optimizers do not jointly resolve where a failure occurs in a workflow, which mechanism caused it, and how relevant knowledge from third-party Skills should be reused locally. We introduce Workflow-Localized Mechanism Learning (WML). Its Node--Mechanism Attribution identifies the failed workflow node, implicated mechanisms, and smallest valid edit target, routing single-mechanism defects to L3 resources and relational defects across mechanisms to L2 composition protocols. A six-module Workflow-Guided Skill Optimization (WGSO) loop then selects provenance- and scope-aware third-party knowledge, applies bounded patches, evaluates candidates, and stores verified outcomes in optimizer-side memory. On SpreadsheetBench, WML reaches 90.33 +/- 1.53 and 74.67 +/- 3.51 Hard Accuracy with DeepSeek and Qwen3.6-Flash, respectively; without additional optimization, the learned Skills transfer to WikiTableQuestions with 84.00 +/- 2.00 and 83.00 +/- 2.00 Denotation Accuracy. On Compiler-Supported50, WML attains both the highest hard-PASS rate and the lowest cost per successful task; compiled execution sharply reduces tokens and calls relative to a direct SkillAgent while retaining most of its successful tasks. Code and artifacts are available at https://github.com/xiaolin9595/workflow-localized-mechanism-learning.