<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-n">
    <titleInfo>
        <title>In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seungkyu</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nalim</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yohan</namePart>
        <namePart type="family">Jo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Tool agents—LLM-based systems that interact with external APIs—offer a way to execute real-world tasks. However, as tasks become increasingly complex, these agents struggle to identify and call the correct APIs in the proper order. To tackle this problem, we investigate converting API documentation into a structured API graph that captures API dependencies and leveraging it for multi-tool queries that require compositional API calls. To support this, we introduce In-N-Out, the first expert-annotated dataset of API graphs built from two real-world API benchmarks and their documentation. Using In-N-Out significantly improves performance on both tool retrieval and multi-tool query generation, nearly doubling that of LLMs using documentation alone. Moreover, graphs generated by models fine-tuned on In-N-Out close 90% of this gap, showing that our dataset helps models learn to comprehend API documentation and parameter relationships. Our findings highlight the promise of using explicit API graphs for tool agents and the utility of In-N-Out as a valuable resource. We release our dataset and code at https://github.com/holi-lab/In-N-Out-API-Graph.</abstract>
    <identifier type="citekey">lee-etal-2026-n</identifier>
    <identifier type="doi">10.1162/tacl.a.694</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.45/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>1008</start>
            <end>1027</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents
%A Lee, Seungkyu
%A Kim, Nalim
%A Jo, Yohan
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F lee-etal-2026-n
%X Tool agents—LLM-based systems that interact with external APIs—offer a way to execute real-world tasks. However, as tasks become increasingly complex, these agents struggle to identify and call the correct APIs in the proper order. To tackle this problem, we investigate converting API documentation into a structured API graph that captures API dependencies and leveraging it for multi-tool queries that require compositional API calls. To support this, we introduce In-N-Out, the first expert-annotated dataset of API graphs built from two real-world API benchmarks and their documentation. Using In-N-Out significantly improves performance on both tool retrieval and multi-tool query generation, nearly doubling that of LLMs using documentation alone. Moreover, graphs generated by models fine-tuned on In-N-Out close 90% of this gap, showing that our dataset helps models learn to comprehend API documentation and parameter relationships. Our findings highlight the promise of using explicit API graphs for tool agents and the utility of In-N-Out as a valuable resource. We release our dataset and code at https://github.com/holi-lab/In-N-Out-API-Graph.
%R 10.1162/tacl.a.694
%U https://aclanthology.org/2026.tacl-1.45/
%U https://doi.org/10.1162/tacl.a.694
%P 1008-1027

Markdown (Informal)

[In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents](https://aclanthology.org/2026.tacl-1.45/) (Lee et al., TACL 2026)

• In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents (Lee et al., TACL 2026)

ACL

• Seungkyu Lee, Nalim Kim, and Yohan Jo. 2026. In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents. Transactions of the Association for Computational Linguistics, 14:1008–1027.