<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2026-toolfuse">
    <titleInfo>
        <title>ToolFuse: Documentation-Intent Fusion for Training-Free Tool Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shao-Cheng</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shui-Hsiang</namePart>
        <namePart type="family">Hsu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chen-Jui</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yao-Chung</namePart>
        <namePart type="family">Fan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>Tool retrieval is a necessary first step for tool-augmented LLMs once the set of available tools grows to thousands or more, and itscentral difficulty stems from two gaps. A user query states what the user wants to accomplish in task-centric language, whereas tooldocumentation describes functionality, parameters, and calling conditions in function-centric terms. This low lexical overlap produces aQuery-Documentation Mismatch. Complex queries also bundle several functional needs at once, while a single tool usually covers only one,producing a Multi-Intent Query Mismatch. We present ToolFuse, a training-free framework that addresses each gap on a different side ofretrieval. On the tool side, Complementarity-based Semantic Fusion treats tool documentation and LLM-generated synthetic intent as adocumentation view and an intent view of the same tool, encodes them separately, and assigns each tool a fusion weight from the geometriccomplementarity between its two views in vector space, without fine-tuning the frozen dense encoder. On the query side, QueryDecomposition splits a multi-intent query into focused sub-queries, retrieves for each, and aggregates the results with rank-aware round-robin. On ToolBench, the full ToolFuse raises the Per-Split average NDCG@5 of Qwen3-Embedding-0.6B from 64.72 to 75.49, with consistentgains across three additional dense encoder backbones.</abstract>
    <identifier type="citekey">lu-etal-2026-toolfuse</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.99/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1420</start>
            <end>1443</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ToolFuse: Documentation-Intent Fusion for Training-Free Tool Retrieval
%A Lu, Shao-Cheng
%A Hsu, Shui-Hsiang
%A Yu, Chen-Jui
%A Fan, Yao-Chung
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F lu-etal-2026-toolfuse
%X Tool retrieval is a necessary first step for tool-augmented LLMs once the set of available tools grows to thousands or more, and itscentral difficulty stems from two gaps. A user query states what the user wants to accomplish in task-centric language, whereas tooldocumentation describes functionality, parameters, and calling conditions in function-centric terms. This low lexical overlap produces aQuery-Documentation Mismatch. Complex queries also bundle several functional needs at once, while a single tool usually covers only one,producing a Multi-Intent Query Mismatch. We present ToolFuse, a training-free framework that addresses each gap on a different side ofretrieval. On the tool side, Complementarity-based Semantic Fusion treats tool documentation and LLM-generated synthetic intent as adocumentation view and an intent view of the same tool, encodes them separately, and assigns each tool a fusion weight from the geometriccomplementarity between its two views in vector space, without fine-tuning the frozen dense encoder. On the query side, QueryDecomposition splits a multi-intent query into focused sub-queries, retrieves for each, and aggregates the results with rank-aware round-robin. On ToolBench, the full ToolFuse raises the Per-Split average NDCG@5 of Qwen3-Embedding-0.6B from 64.72 to 75.49, with consistentgains across three additional dense encoder backbones.
%U https://aclanthology.org/2026.realm-1.99/
%P 1420-1443

Markdown (Informal)

[ToolFuse: Documentation-Intent Fusion for Training-Free Tool Retrieval](https://aclanthology.org/2026.realm-1.99/) (Lu et al., REALM 2026)

• ToolFuse: Documentation-Intent Fusion for Training-Free Tool Retrieval (Lu et al., REALM 2026)

ACL

• Shao-Cheng Lu, Shui-Hsiang Hsu, Chen-Jui Yu, and Yao-Chung Fan. 2026. ToolFuse: Documentation-Intent Fusion for Training-Free Tool Retrieval. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 1420–1443, Budapest, Hungary. Association for Computational Linguistics.