Multi-Agent Based Character Simulation for Story Writing

Tian Yu; Ken Shi; Zixin Zhao; Gerald Penn

doi:10.18653/v1/2025.in2writing-1.9

Multi-Agent Based Character Simulation for Story Writing

Tian Yu, Ken Shi, Zixin Zhao, Gerald Penn

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

This work proposes a novel multi-agent story-generation system that writes stories from a narrative plan. Traditional approaches tend to generate a section of text directly from its outline. Our system, by contrast, divides this elaboration process into role-play and rewrite steps, where the former step enacts the story in chronological order with LLM-backed character agents, and the latter step refines the role-play result to align with a narrative plan. We show that the stories produced by our system are preferable to two other LLM-based story-generation approaches. We attribute this advancement to the benefits of incorporating a character-based simulation strategy.

Anthology ID:: 2025.in2writing-1.9
Volume:: Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025)
Month:: May
Year:: 2025
Address:: Albuquerque, New Mexico, US
Editors:: Vishakh Padmakumar, Katy Gero, Thiemo Wambsganss, Sarah Sterman, Ting-Hao Huang, David Zhou, John Chung
Venues:: In2Writing | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 87–108
Language:
URL:: https://aclanthology.org/2025.in2writing-1.9/
DOI:: 10.18653/v1/2025.in2writing-1.9
Bibkey:
Cite (ACL):: Tian Yu, Ken Shi, Zixin Zhao, and Gerald Penn. 2025. Multi-Agent Based Character Simulation for Story Writing. In Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025), pages 87–108, Albuquerque, New Mexico, US. Association for Computational Linguistics.
Cite (Informal):: Multi-Agent Based Character Simulation for Story Writing (Yu et al., In2Writing 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.in2writing-1.9.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{yu-etal-2025-multi,
    title = "Multi-Agent Based Character Simulation for Story Writing",
    author = "Yu, Tian  and
      Shi, Ken  and
      Zhao, Zixin  and
      Penn, Gerald",
    editor = "Padmakumar, Vishakh  and
      Gero, Katy  and
      Wambsganss, Thiemo  and
      Sterman, Sarah  and
      Huang, Ting-Hao  and
      Zhou, David  and
      Chung, John",
    booktitle = "Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico, US",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.in2writing-1.9/",
    doi = "10.18653/v1/2025.in2writing-1.9",
    pages = "87--108",
    ISBN = "979-8-89176-239-8",
    abstract = "This work proposes a novel multi-agent story-generation system that writes stories from a narrative plan. Traditional approaches tend to generate a section of text directly from its outline. Our system, by contrast, divides this elaboration process into role-play and rewrite steps, where the former step enacts the story in chronological order with LLM-backed character agents, and the latter step refines the role-play result to align with a narrative plan. We show that the stories produced by our system are preferable to two other LLM-based story-generation approaches. We attribute this advancement to the benefits of incorporating a character-based simulation strategy."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2025-multi">
    <titleInfo>
        <title>Multi-Agent Based Character Simulation for Story Writing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tian</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ken</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zixin</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gerald</namePart>
        <namePart type="family">Penn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vishakh</namePart>
            <namePart type="family">Padmakumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Katy</namePart>
            <namePart type="family">Gero</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thiemo</namePart>
            <namePart type="family">Wambsganss</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sarah</namePart>
            <namePart type="family">Sterman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ting-Hao</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Zhou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">John</namePart>
            <namePart type="family">Chung</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico, US</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-239-8</identifier>
    </relatedItem>
    <abstract>This work proposes a novel multi-agent story-generation system that writes stories from a narrative plan. Traditional approaches tend to generate a section of text directly from its outline. Our system, by contrast, divides this elaboration process into role-play and rewrite steps, where the former step enacts the story in chronological order with LLM-backed character agents, and the latter step refines the role-play result to align with a narrative plan. We show that the stories produced by our system are preferable to two other LLM-based story-generation approaches. We attribute this advancement to the benefits of incorporating a character-based simulation strategy.</abstract>
    <identifier type="citekey">yu-etal-2025-multi</identifier>
    <identifier type="doi">10.18653/v1/2025.in2writing-1.9</identifier>
    <location>
        <url>https://aclanthology.org/2025.in2writing-1.9/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>87</start>
            <end>108</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Multi-Agent Based Character Simulation for Story Writing
%A Yu, Tian
%A Shi, Ken
%A Zhao, Zixin
%A Penn, Gerald
%Y Padmakumar, Vishakh
%Y Gero, Katy
%Y Wambsganss, Thiemo
%Y Sterman, Sarah
%Y Huang, Ting-Hao
%Y Zhou, David
%Y Chung, John
%S Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, US
%@ 979-8-89176-239-8
%F yu-etal-2025-multi
%X This work proposes a novel multi-agent story-generation system that writes stories from a narrative plan. Traditional approaches tend to generate a section of text directly from its outline. Our system, by contrast, divides this elaboration process into role-play and rewrite steps, where the former step enacts the story in chronological order with LLM-backed character agents, and the latter step refines the role-play result to align with a narrative plan. We show that the stories produced by our system are preferable to two other LLM-based story-generation approaches. We attribute this advancement to the benefits of incorporating a character-based simulation strategy.
%R 10.18653/v1/2025.in2writing-1.9
%U https://aclanthology.org/2025.in2writing-1.9/
%U https://doi.org/10.18653/v1/2025.in2writing-1.9
%P 87-108

Download as File

Markdown (Informal)

[Multi-Agent Based Character Simulation for Story Writing](https://aclanthology.org/2025.in2writing-1.9/) (Yu et al., In2Writing 2025)

Multi-Agent Based Character Simulation for Story Writing (Yu et al., In2Writing 2025)

ACL

Tian Yu, Ken Shi, Zixin Zhao, and Gerald Penn. 2025. Multi-Agent Based Character Simulation for Story Writing. In Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025), pages 87–108, Albuquerque, New Mexico, US. Association for Computational Linguistics.