Metraipolis › archive › dc_d1724335bb00

CompSkill: Compiling Execution Experience for Skill Retrieval — arXiv:2611.01115

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01115
License (as archived)
CC0-1.0
Archived
2026-11-03T11:09:51.783Z
SHA-256 of the archived text
7148fe16ad9a229c9726d7ee96a7696b3e059c4a89798a648397f11a20611d8b
Stable URL of this page
https://metraipolis.com/documento/dc_d1724335bb00

How to cite

CompSkill: Compiling Execution Experience for Skill Retrieval — arXiv:2611.01115 — arXiv (en), https://arxiv.org/abs/2611.01115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1724335bb00 (Metraipolis archive dc_d1724335bb00, sha256 7148fe16ad9a229c9726d7ee96a7696b3e059c4a89798a648397f11a20611d8b)
BibTeX
@misc{dcd1724335bb00,
  title = {CompSkill: Compiling Execution Experience for Skill Retrieval — arXiv:2611.01115},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01115},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1724335bb00; sha256 7148fe16ad9a229c9726d7ee96a7696b3e059c4a89798a648397f11a20611d8b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents increasingly rely on skill documents, yet most retrievers rank them by description alone and ignore what earlier executions revealed, even though a relevant skill can hurt execution. We present CompSkill, which indexes skills with learned 512-d keys and compiles matched same-task comparisons into skill offsets and capped key residuals (KeyOpt), so experience changes which document the executor receives, never its text. Under a logistic outcome model with unknown task difficulty, matched comparisons cancel that difficulty and only discordant ones carry information; on support executions, predictions improve with each discordant task. An experience hypergraph keeps each comparison with its executor and document versions, recalls missed skills and grounds a cited review. Compact keys raise SkillRet NDCG@10 from 64.0 to 70.9 at one eighth of the dimension. With one document, CompSkill completes 256 and 260 of 332 ToolQA tasks with GPT-5.6-luna and DeepSeek-V4.1-Flash, respectively, more than every baseline, and stays on par with the strongest baselines on AppWorld and ALFWorld. On 332 newly generated ToolQA tasks, it completes 256 with GPT-5.6-luna, significantly more than BM25, SkillRet-8B, Tool2Vec and RankGPT; over all 844 ToolQA tasks, it completes 24 more than the strongest baseline. Selection matters beyond relevance: pairing the right guide with a same-database sibling instead of another database's guide costs 8 of 96 tasks. Code, models and support data: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.01115 — 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 2026-11-03T10:59:52.285Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).