Metraipolis › archive › dc_3ea4cd40fd2b

SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence — arXiv:2609.26863

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26863
License (as archived)
CC0-1.0
Archived
2026-10-08T08:57:17.447Z
SHA-256 of the archived text
089937cae13aaa99e84418b43140d8e8d524491779c40ddf94da20fcc3d49f85
Stable URL of this page
https://metraipolis.com/documento/dc_3ea4cd40fd2b

How to cite

SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence — arXiv:2609.26863 — arXiv (en), https://arxiv.org/abs/2609.26863 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ea4cd40fd2b (Metraipolis archive dc_3ea4cd40fd2b, sha256 089937cae13aaa99e84418b43140d8e8d524491779c40ddf94da20fcc3d49f85)
BibTeX
@misc{dc3ea4cd40fd2b,
  title = {SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence — arXiv:2609.26863},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26863},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ea4cd40fd2b; sha256 089937cae13aaa99e84418b43140d8e8d524491779c40ddf94da20fcc3d49f85},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26863. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model agents increasingly retrieve reusable Skills and inject them into the active context. However, a retrieved Skill can be relevant yet unnecessary, costly, or even harmful in the current execution state. We present SkillApt, a post-retrieval activation framework that decides whether a retrieved Skill should actually be loaded. SkillApt builds execution evidence from matched WITH/WITHOUT runs and uses outcomes from similar historical states to make a LOAD/ABSTAIN decision for each candidate Skill. On the frozen confirmatory SRA-Bench evaluation, SkillApt-E achieved the same observed accuracy as BM25 Top-1 (0.838 vs. 0.838) while reducing the Skill activation rate from 100% to 31.5% and mean token usage by 74.3%. Further diagnostics show that both Skill utility and the learnability of its activation boundary vary across base models. These results suggest that Skill retrieval and Skill activation should be treated as separate decisions: retrieval identifies which Skill may be relevant, while SkillApt determines whether using it is worthwhile in the current state.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.26863 — 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 2026-10-08T08:03:18.921Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).