Metraipolis › archive › dc_f4187de0b3cb
When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval — arXiv:2608.16502
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16502
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:41:39.996Z
- SHA-256 of the archived text
91026ffb21d9e5e52cee65c73b0fb22849a38914338316f3cd5df85efbc9de4d- Stable URL of this page
https://metraipolis.com/documento/dc_f4187de0b3cb
How to cite
When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval — arXiv:2608.16502 — arXiv (en), https://arxiv.org/abs/2608.16502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4187de0b3cb (Metraipolis archive dc_f4187de0b3cb, sha256 91026ffb21d9e5e52cee65c73b0fb22849a38914338316f3cd5df85efbc9de4d)
BibTeX
@misc{dcf4187de0b3cb,
title = {When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval — arXiv:2608.16502},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16502},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4187de0b3cb; sha256 91026ffb21d9e5e52cee65c73b0fb22849a38914338316f3cd5df85efbc9de4d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large-scale agents increasingly rely on retrieval to access external capabilities. We study this retrieval gate in structured tools and APIs, a measurable class of tool-backed executable skills that must be surfaced before an agent can plan, incorporate, or act. In this setting the retrieval layer can silently fail even when the capability corpus is fixed: on ToolRet, a retriever fine-tuned on one source-specific slice collapses on another source-specific slice of the same benchmark, with FT-1100 despite its higher lexical overlap with the gold tools. We call this failure mode source-style collapse. Query-side TF-IDF fingerprints flag source styles on which the fine-tuned retriever is likely to fail better than semantic or length-based proxies, giving a cheap signal for mismatch over a fixed tool corpus. We propose ToolScout, a source-aware routing method that uses this signal as a routing guard: on the mixed 4,996-query stream, TF-IDF-based routing raises coverage from 22.3% to 86.1%, and across five collapsed sources 20 matched examples raise the coverage-weighted global top-1 proxy from 1.3% to 53.9%. The same failure and routing behaviors persist when tools are rerendered as executable skill cards, which rules out raw API-schema format as the sole cause. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.16502 — 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 2026-10-18T19:02:44.179Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).