<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-ng-2025-constrained">
    <titleInfo>
        <title>A Constrained Text Revision Agent via Iterative Planning and Searching</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hannan</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hwee</namePart>
        <namePart type="given">Tou</namePart>
        <namePart type="family">Ng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Existing text revision systems are capable of generating fluent and coherent text, but struggle with constrained text revision (CTR), which requires adherence to specific constraints. Furthermore, adapting these systems to diverse constraints is challenging. To bridge this gap, we introduce TRIPS, a Text Revision agent via Iterative Planning and Searching, focusing on CTR. TRIPS utilizes a planner, a reviser (i.e., a large language model), and adaptable tools to generate revisions tailored to different scenarios. Specifically, we propose an iterative self-training alignment method to construct the planner, which generates tool usage and text revision plans. Furthermore, we propose Tool-Guided Monte Carlo Tree Search (TG-MCTS), a novel CTR algorithm that extends MCTS with tool-guided expansion and evaluation, enabling the search for optimal revision strategies across various scenarios. To evaluate TRIPS, we introduce ConsTRev, a dataset with multi-level constrained instructions for paragraph-level revision. Experimental results show that TRIPS outperforms baselines in both constraint adherence and revision quality. Furthermore, TRIPS exhibits robust performance across diverse use cases, including plain text and LaTeX revision.</abstract>
    <identifier type="citekey">cao-ng-2025-constrained</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.1377</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.1377/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>26859</start>
            <end>26882</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Constrained Text Revision Agent via Iterative Planning and Searching
%A Cao, Hannan
%A Ng, Hwee Tou
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F cao-ng-2025-constrained
%X Existing text revision systems are capable of generating fluent and coherent text, but struggle with constrained text revision (CTR), which requires adherence to specific constraints. Furthermore, adapting these systems to diverse constraints is challenging. To bridge this gap, we introduce TRIPS, a Text Revision agent via Iterative Planning and Searching, focusing on CTR. TRIPS utilizes a planner, a reviser (i.e., a large language model), and adaptable tools to generate revisions tailored to different scenarios. Specifically, we propose an iterative self-training alignment method to construct the planner, which generates tool usage and text revision plans. Furthermore, we propose Tool-Guided Monte Carlo Tree Search (TG-MCTS), a novel CTR algorithm that extends MCTS with tool-guided expansion and evaluation, enabling the search for optimal revision strategies across various scenarios. To evaluate TRIPS, we introduce ConsTRev, a dataset with multi-level constrained instructions for paragraph-level revision. Experimental results show that TRIPS outperforms baselines in both constraint adherence and revision quality. Furthermore, TRIPS exhibits robust performance across diverse use cases, including plain text and LaTeX revision.
%R 10.18653/v1/2025.findings-acl.1377
%U https://aclanthology.org/2025.findings-acl.1377/
%U https://doi.org/10.18653/v1/2025.findings-acl.1377
%P 26859-26882

Markdown (Informal)

[A Constrained Text Revision Agent via Iterative Planning and Searching](https://aclanthology.org/2025.findings-acl.1377/) (Cao & Ng, Findings 2025)

• A Constrained Text Revision Agent via Iterative Planning and Searching (Cao & Ng, Findings 2025)

ACL

• Hannan Cao and Hwee Tou Ng. 2025. A Constrained Text Revision Agent via Iterative Planning and Searching. In Findings of the Association for Computational Linguistics: ACL 2025, pages 26859–26882, Vienna, Austria. Association for Computational Linguistics.