CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning Jun 08, 2026

Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition

arXiv AI Archived Jun 08, 2026 ✓ Full text saved

arXiv:2606.06893v1 Announce Type: new Abstract: 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 sa

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Artificial Intelligence [Submitted on 5 Jun 2026] Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition Yuyang Zhang, Xinyuan Han, Xudong Jiang, Run Wang 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. Comments: 10 pages, 2 figures Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.06893 [cs.AI]   (or arXiv:2606.06893v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.06893 Focus to learn more Submission history From: Yuyang Zhang [view email] [v1] Fri, 5 Jun 2026 04:19:57 UTC (770 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
    💬 Team Notes
    Article Info
    Source
    arXiv AI
    Category
    ◬ AI & Machine Learning
    Published
    Jun 08, 2026
    Archived
    Jun 08, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗