Metraipolis › archive › dc_63c7c2d3dfcb
Think with Skills: Pseudocode Planning Before Execution for Advanced Reasoners — arXiv:2611.02830
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02830
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:53:48.356Z
- SHA-256 of the archived text
6a369ebe81944a6124d23233902b9dc523230a72f88aaa81100ffdcba8065038- Stable URL of this page
https://metraipolis.com/documento/dc_63c7c2d3dfcb
How to cite
Think with Skills: Pseudocode Planning Before Execution for Advanced Reasoners — arXiv:2611.02830 — arXiv (en), https://arxiv.org/abs/2611.02830 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63c7c2d3dfcb (Metraipolis archive dc_63c7c2d3dfcb, sha256 6a369ebe81944a6124d23233902b9dc523230a72f88aaa81100ffdcba8065038)
BibTeX
@misc{dc63c7c2d3dfcb,
title = {Think with Skills: Pseudocode Planning Before Execution for Advanced Reasoners — arXiv:2611.02830},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02830},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63c7c2d3dfcb; sha256 6a369ebe81944a6124d23233902b9dc523230a72f88aaa81100ffdcba8065038},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02830. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Language model agents often struggle with complex tasks even when equipped with expert-written skills. Such skills encode declarative knowledge, whereas successful execution requires procedural knowledge tailored to the task at hand. Natural language skills may leave conditions and dependencies implicit, and tasks involving multiple skills further require agents to coordinate intermediate results and execution order. We introduce Think with Skills, a method that trains reasoning models to turn relevant skill descriptions into task-specific pseudocode plans before execution. The pseudocode explicitly represents operations, conditions, intermediate results, and dependencies, providing a structured bridge from skill descriptions to agent actions. We construct training data that pairs tasks and skills with pseudocode plans and execution trajectories, use supervised fine tuning to initialize this behavior, and further optimize end-to-end task performance with Group Relative Policy Optimization. On SkillsBench, Think with Skills raises task success from 35.0% to 62.0%. These results show that proceduralizing expert knowledge before execution substantially improves skill use. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.02830 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:49:38.391Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).