Metraipolis › archive › dc_dce9ebac413d

Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evaluation — arXiv:2608.28241

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28241
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:31.519Z
SHA-256 of the archived text
6a8e16773d45cb18db08ca8265688483a4bf497d1296923a117394969ea77ee2
Stable URL of this page
https://metraipolis.com/documento/dc_dce9ebac413d

How to cite

Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evaluation — arXiv:2608.28241 — arXiv (en), https://arxiv.org/abs/2608.28241 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dce9ebac413d (Metraipolis archive dc_dce9ebac413d, sha256 6a8e16773d45cb18db08ca8265688483a4bf497d1296923a117394969ea77ee2)
BibTeX
@misc{dcdce9ebac413d,
  title = {Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evaluation — arXiv:2608.28241},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28241},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dce9ebac413d; sha256 6a8e16773d45cb18db08ca8265688483a4bf497d1296923a117394969ea77ee2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28241. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The rapid expansion of reusable skill repositories makes skill routing a critical capability for large language model (LLM) agents. Existing methods treat routing as task-only semantic matching. However, when users with incompatible constraints issue an identical request, this assumption conflates task relevance with skill suitability: a task-only router can select a semantically plausible skill that is unsuitable for the requesting user. To expose this failure mode, we formulate \textit{personalized skill routing} as profile-conditioned retrieval, in which relevance depends jointly on the task and the user profile. We first introduce a profile-counterfactual benchmark, in which the task is held fixed while changes in the user profile induce changes in the reference skill. We further construct paired counterfactual supervision and propose SkillFeed, a progressive retrieve-and-rerank framework that first establishes task--skill alignment and then learns profile-conditioned discrimination. By retrieving body-level evidence and reranking semantically similar but profile-conflicting candidates, SkillFeed identifies skills that satisfy both task requirements and user constraints. On SkillFeed-Bench, SkillFeed attains 75.1\% top-1 retrieval accuracy, a 23.1-point improvement over the corresponding pretrained routing baseline. Adding profile conditioning yields a 35.1-point gain on queries where user profile changes the reference skill. This contrast shows that user profiles are most consequential precisely when they change skill suitability. Our website is publicly available at this http URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28241 — 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 2026-10-17T10:33:42.406Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).