<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sullivan-etal-2025-procedural">
    <titleInfo>
        <title>Procedural Environment Generation for Tool-Use Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Sullivan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mareike</namePart>
        <namePart type="family">Hartmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Koller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Although the power of LLM tool-use agents has ignited a flurry of recent research in this area, the curation of tool-use training data remains an open problem—especially for online RL training. Existing approaches to synthetic tool-use data generation tend to be non-interactive and/or non-compositional. We introduce RandomWorld, a pipeline for the procedural generation of interactive tools and compositional tool-use data. We show that models tuned via SFT and RL on synthetic RandomWorld data improve on a range of tool-use benchmarks, and set the new SoTA for two metrics on the NESTFUL dataset. Further experiments show that downstream performance scales with the amount of RandomWorld-generated training data, opening up the possibility of further improvement through the use of entirely synthetic data.</abstract>
    <identifier type="citekey">sullivan-etal-2025-procedural</identifier>
    <identifier type="doi">10.18653/v1/2025.emnlp-main.936</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.936/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>18544</start>
            <end>18562</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Procedural Environment Generation for Tool-Use Agents
%A Sullivan, Michael
%A Hartmann, Mareike
%A Koller, Alexander
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F sullivan-etal-2025-procedural
%X Although the power of LLM tool-use agents has ignited a flurry of recent research in this area, the curation of tool-use training data remains an open problem—especially for online RL training. Existing approaches to synthetic tool-use data generation tend to be non-interactive and/or non-compositional. We introduce RandomWorld, a pipeline for the procedural generation of interactive tools and compositional tool-use data. We show that models tuned via SFT and RL on synthetic RandomWorld data improve on a range of tool-use benchmarks, and set the new SoTA for two metrics on the NESTFUL dataset. Further experiments show that downstream performance scales with the amount of RandomWorld-generated training data, opening up the possibility of further improvement through the use of entirely synthetic data.
%R 10.18653/v1/2025.emnlp-main.936
%U https://aclanthology.org/2025.emnlp-main.936/
%U https://doi.org/10.18653/v1/2025.emnlp-main.936
%P 18544-18562

Markdown (Informal)

[Procedural Environment Generation for Tool-Use Agents](https://aclanthology.org/2025.emnlp-main.936/) (Sullivan et al., EMNLP 2025)

• Procedural Environment Generation for Tool-Use Agents (Sullivan et al., EMNLP 2025)

ACL

• Michael Sullivan, Mareike Hartmann, and Alexander Koller. 2025. Procedural Environment Generation for Tool-Use Agents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 18544–18562, Suzhou, China. Association for Computational Linguistics.