Metraipolis › archive › dc_66bfa3e62bae
From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation — arXiv:2610.20388
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20388
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:02:28.957Z
- SHA-256 of the archived text
9758bcbceee4357620e087854af583259a05917aa54c60cccb09dc499e7cddfe- Stable URL of this page
https://metraipolis.com/documento/dc_66bfa3e62bae
How to cite
From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation — arXiv:2610.20388 — arXiv (en), https://arxiv.org/abs/2610.20388 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66bfa3e62bae (Metraipolis archive dc_66bfa3e62bae, sha256 9758bcbceee4357620e087854af583259a05917aa54c60cccb09dc499e7cddfe)
BibTeX
@misc{dc66bfa3e62bae,
title = {From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation — arXiv:2610.20388},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20388},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66bfa3e62bae; sha256 9758bcbceee4357620e087854af583259a05917aa54c60cccb09dc499e7cddfe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20388. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents increasingly face tasks from unseen domains and execution contexts, making zero-shot tool selection essential for identifying tools that can satisfy task requirements. Existing dominant methods mainly rely on relevance ranking, but semantic matching alone cannot ensure that a tool is functionally compatible or remains applicable in a new context. We preliminarily identify a \emph{transfer-validity gap}, where semantically relevant tools may still fail to satisfy functional or contextual requirements after transfer. To address this gap, we propose \methodname{}, a progressive validation framework that complements semantic relevance with endpoint-grounded functional compatibility and task-conditioned contextual evidence. Across cross-domain and cross-dataset transfer, \methodname{} consistently improves capability ranking, with larger gains under functional or contextual ambiguity. Ablation results further confirm the complementary contributions of functional and contextual validation.
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/2610.20388 — 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 2026-10-15T19:35:48.304Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).