Abstract
Agent Skills package reusable procedural knowledge as external artifacts for frozen language-model agents. However, 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 GitHub.
Blogger's Review: The WML approach effectively identifies failure points in workflows through Node–Mechanism Attribution and utilizes the WGSO loop for knowledge reuse, demonstrating optimization potential in complex tasks, especially in scenarios involving multi-mechanism interactions. Further exploration of its application possibilities is warranted.