<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-glass-2026-beyond">
    <titleInfo>
        <title>Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Fang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="given">R</namePart>
        <namePart type="family">Glass</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals and technical documentation, and the limited capacity of fixed-size embeddings to model combinatorial tool compositions. To address these challenges, we propose ToolQP, a lightweight framework that models retrieval as iterative query planning. Instead of single-shot matching, ToolQP decomposes instructions into sub-tasks and dynamically generates queries to interact with the retriever, effectively bridging the semantic gap by targeting the specific sub-tasks required for composition. We train ToolQP using synthetic query trajectories followed by optimization with Reinforcement Learning with Verifiable Rewards (RLVR). Experiments demonstrate that ToolQP achieves state-of-the-art performance, exhibiting superior zero-shot generalization, robustness across diverse retrievers, and significant improvements in downstream agentic execution.</abstract>
    <identifier type="citekey">fang-glass-2026-beyond</identifier>
    <identifier type="doi">10.18653/v1/2026.findings-acl.2090</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.2090/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>42119</start>
            <end>42144</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning
%A Fang, Wei
%A Glass, James R.
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F fang-glass-2026-beyond
%X LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals and technical documentation, and the limited capacity of fixed-size embeddings to model combinatorial tool compositions. To address these challenges, we propose ToolQP, a lightweight framework that models retrieval as iterative query planning. Instead of single-shot matching, ToolQP decomposes instructions into sub-tasks and dynamically generates queries to interact with the retriever, effectively bridging the semantic gap by targeting the specific sub-tasks required for composition. We train ToolQP using synthetic query trajectories followed by optimization with Reinforcement Learning with Verifiable Rewards (RLVR). Experiments demonstrate that ToolQP achieves state-of-the-art performance, exhibiting superior zero-shot generalization, robustness across diverse retrievers, and significant improvements in downstream agentic execution.
%R 10.18653/v1/2026.findings-acl.2090
%U https://aclanthology.org/2026.findings-acl.2090/
%U https://doi.org/10.18653/v1/2026.findings-acl.2090
%P 42119-42144

Markdown (Informal)

[Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning](https://aclanthology.org/2026.findings-acl.2090/) (Fang & Glass, Findings 2026)

• Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning (Fang & Glass, Findings 2026)

ACL

• Wei Fang and James R. Glass. 2026. Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 42119–42144, San Diego, California, United States. Association for Computational Linguistics.