<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-tool">
    <titleInfo>
        <title>When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yiqi</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joseph</namePart>
        <namePart type="family">James</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenghao</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenghua</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>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 falling to 0.7% coverage on APIGen despite its higher lexical overlap with the gold tools. We call this failure mode source-style collapse. Query-side TF-IDF centroid distance identifies low-coverage transfer sources more reliably than semantic- or length-based proxies, providing a lightweight compatibility signal over a fixed tool corpus. We propose ToolScout, a source-aware routing method that uses this signal as a routing criterion: 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-shot source-specific adaptation, using 20 training queries per source, raises the coverage-weighted global top-1 proxy from 1.3% to 53.9%. The same failure and routing behaviors persist under executable skill-card rendering, showing that source-style collapse also occurs with this capability representation.</abstract>
    <identifier type="citekey">liu-etal-2026-tool</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.60/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>1181</start>
            <end>1203</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval
%A Liu, Yiqi
%A James, Joseph
%A Wang, Yang
%A Xiao, Chenghao
%A Lin, Chenghua
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F liu-etal-2026-tool
%X 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 falling to 0.7% coverage on APIGen despite its higher lexical overlap with the gold tools. We call this failure mode source-style collapse. Query-side TF-IDF centroid distance identifies low-coverage transfer sources more reliably than semantic- or length-based proxies, providing a lightweight compatibility signal over a fixed tool corpus. We propose ToolScout, a source-aware routing method that uses this signal as a routing criterion: 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-shot source-specific adaptation, using 20 training queries per source, raises the coverage-weighted global top-1 proxy from 1.3% to 53.9%. The same failure and routing behaviors persist under executable skill-card rendering, showing that source-style collapse also occurs with this capability representation.
%U https://aclanthology.org/2026.findings-aacl.60/
%P 1181-1203

Markdown (Informal)

[When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval](https://aclanthology.org/2026.findings-aacl.60/) (Liu et al., Findings 2026)

• When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval (Liu et al., Findings 2026)

ACL

• Yiqi Liu, Joseph James, Yang Wang, Chenghao Xiao, and Chenghua Lin. 2026. When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 1181–1203, Hengqin, China. Association for Computational Linguistics.