工作流局部机制学习：结构化智能体技能的归因引导修复与知识重用
Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills
- SZU（深圳大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
研究针对智能体技能中工作流故障问题，引入工作流局部机制学习（WML）。其节点 - 机制归因可识别故障节点等，再经工作流引导技能优化（WGSO）循环处理。在多个数据集上实验，WML取得较好准确率、通过率等，还减少了令牌和调用。
中文摘要 AI 辅助
智能体技能将可重用的过程性知识作为外部工件用于冻结语言模型智能体，但现有优化器无法联合解决工作流中故障发生的位置、导致故障的机制以及如何在本地重用第三方技能的相关知识。为此引入工作流局部机制学习（WML）。其节点-机制归因可识别失败的工作流节点、相关机制和最小有效编辑目标，将单机制缺陷路由到L3资源，将跨机制的关系缺陷路由到L2组合协议。然后，一个由六个模块组成的工作流引导技能优化（WGSO）循环会选择有来源和范围意识的第三方知识，应用有界补丁，评估候选方案，并将经过验证的结果存储在优化器端内存中。在SpreadsheetBench上，WML分别使用DeepSeek和Qwen3.6-Flash达到了90.33 +/- 1.53和74.67 +/- 3.51的硬准确率；在没有额外优化情况下，学到的技能转移到WikiTableQuestions上的指称准确率分别为84.00 +/- 2.00和83.00 +/- 2.00。在Compiler-Supported50上，WML实现了最高的硬通过率和最低的每个成功任务成本；编译执行相对于直接的SkillAgent大幅减少了令牌和调用，同时保留了大部分成功任务。
英文摘要
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.
