Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
arXiv AIArchived 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?)