<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-encouraging">
    <titleInfo>
        <title>Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhiwei</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yong</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenqing</namePart>
        <namePart type="family">Wang</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saloni</namePart>
            <namePart type="family">Potdar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lina</namePart>
            <namePart type="family">Rojas-Barahona</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastien</namePart>
            <namePart type="family">Montella</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">979-8-89176-333-3</identifier>
    </relatedItem>
    <abstract>The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent’s performance. However, prevailing training paradigms employ end-to-end, multi-objective optimization that jointly trains both capabilities. This paradigm faces two critical challenges: imbalanced optimization objective allocation and scarcity of verifiable data, making it difficult to enhance the agent’s planning capability. To address these challenges, we propose Reinforcement Learning with Tool-use Rewards (RLTR), a novel framework that decouples the training process to enable a focused, single-objective optimization of the planning module. Crucially, RLTR introduces a reward signal based on tool-use completeness to directly evaluate the quality of tool invocation sequences. This method offers a more direct and reliable training signal than assessing the final response content, thereby obviating the need for verifiable data. Our experiments demonstrate that RLTR achieves an 8%–12% improvement in planning performance compared to end-to-end baselines. Moreover, this enhanced planning capability, in turn, translates to a 5%–6% increase in the final response quality of the overall agent system.</abstract>
    <identifier type="citekey">li-etal-2025-encouraging</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-industry.116/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>1654</start>
            <end>1666</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning
%A Li, Zhiwei
%A Hu, Yong
%A Wang, Wenqing
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F li-etal-2025-encouraging
%X The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent’s performance. However, prevailing training paradigms employ end-to-end, multi-objective optimization that jointly trains both capabilities. This paradigm faces two critical challenges: imbalanced optimization objective allocation and scarcity of verifiable data, making it difficult to enhance the agent’s planning capability. To address these challenges, we propose Reinforcement Learning with Tool-use Rewards (RLTR), a novel framework that decouples the training process to enable a focused, single-objective optimization of the planning module. Crucially, RLTR introduces a reward signal based on tool-use completeness to directly evaluate the quality of tool invocation sequences. This method offers a more direct and reliable training signal than assessing the final response content, thereby obviating the need for verifiable data. Our experiments demonstrate that RLTR achieves an 8%–12% improvement in planning performance compared to end-to-end baselines. Moreover, this enhanced planning capability, in turn, translates to a 5%–6% increase in the final response quality of the overall agent system.
%U https://aclanthology.org/2025.emnlp-industry.116/
%P 1654-1666

Markdown (Informal)

[Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning](https://aclanthology.org/2025.emnlp-industry.116/) (Li et al., EMNLP 2025)

• Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning (Li et al., EMNLP 2025)

ACL

• Zhiwei Li, Yong Hu, and Wenqing Wang. 2025. Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1654–1666, Suzhou (China). Association for Computational Linguistics.