Work2Skill: framework, dataset (WorkDemo-350) and method for reusable GUI agent skills (arXiv:2610.12984v1)
The paper introduces Work2Skill, a framework for capturing human desktop GUI experience and inducing reusable agent skills. It presents WorkRecorder for synchronized multimodal collection (screen, mouse/keyboard, accessibility tree), the WorkDemo-350 dataset of 350 screened demonstrations, and an agentic skill-induction method that improves execution model scores versus a No Skill baseline (mean gains 4.67–10.54 on MyPCBench Bounded Action and 3.11–7.50 on a 286-task OSWorld-Verified subset); code and data are on GitHub.