Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety

Chenghao Li; Xueqin Xiao; Yinuo Xiao; Zihan Xu; Xinzhao Li; Yuxuan Luan; Jiwei Wei; Yang Yang; Chaoning Zhang

Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety

Chenghao Li, Xueqin Xiao, Yinuo Xiao, Zihan Xu, Xinzhao Li, Yuxuan Luan, Jiwei Wei, Yang Yang, Chaoning Zhang

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

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>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

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

Large language models have made role-playing agents viable as interactive characters, virtual companions, game agents, and social actors. The harder problem, however, is not producing one convincing response but sustaining a coherent role through long, changing, and sometimes adversarial interactions. This survey examines recent work on role consistency: the maintenance of identity, character knowledge, expressive style, memory, values, behavioral logic, and safety boundaries over time. We organize the literature around role specification, role-state maintenance, role-aware reasoning, role-consistent alignment, and evaluation.

Anthology ID:: 2026.findings-emnlp.625
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 13129–13145
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.625/
DOI:
Bibkey:
Cite (ACL):: Chenghao Li, Xueqin Xiao, Yinuo Xiao, Zihan Xu, Xinzhao Li, Yuxuan Luan, Jiwei Wei, Yang Yang, and Chaoning Zhang. 2026. Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 13129–13145, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety (Li et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.625.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{li-etal-2026-role-consistency,
    title = "Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety",
    author = "Li, Chenghao  and
      Xiao, Xueqin  and
      Xiao, Yinuo  and
      Xu, Zihan  and
      Li, Xinzhao  and
      Luan, Yuxuan  and
      Wei, Jiwei  and
      Yang, Yang  and
      Zhang, Chaoning",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.625/",
    pages = "13129--13145",
    ISBN = "979-8-89176-462-0",
    abstract = "Large language models have made role-playing agents viable as interactive characters, virtual companions, game agents, and social actors. The harder problem, however, is not producing one convincing response but sustaining a coherent role through long, changing, and sometimes adversarial interactions. This survey examines recent work on role consistency: the maintenance of identity, character knowledge, expressive style, memory, values, behavioral logic, and safety boundaries over time. We organize the literature around role specification, role-state maintenance, role-aware reasoning, role-consistent alignment, and evaluation."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-role-consistency">
    <titleInfo>
        <title>Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chenghao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xueqin</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yinuo</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zihan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinzhao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuxuan</namePart>
        <namePart type="family">Luan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiwei</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chaoning</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Large language models have made role-playing agents viable as interactive characters, virtual companions, game agents, and social actors. The harder problem, however, is not producing one convincing response but sustaining a coherent role through long, changing, and sometimes adversarial interactions. This survey examines recent work on role consistency: the maintenance of identity, character knowledge, expressive style, memory, values, behavioral logic, and safety boundaries over time. We organize the literature around role specification, role-state maintenance, role-aware reasoning, role-consistent alignment, and evaluation.</abstract>
    <identifier type="citekey">li-etal-2026-role-consistency</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.625/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>13129</start>
            <end>13145</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety
%A Li, Chenghao
%A Xiao, Xueqin
%A Xiao, Yinuo
%A Xu, Zihan
%A Li, Xinzhao
%A Luan, Yuxuan
%A Wei, Jiwei
%A Yang, Yang
%A Zhang, Chaoning
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F li-etal-2026-role-consistency
%X Large language models have made role-playing agents viable as interactive characters, virtual companions, game agents, and social actors. The harder problem, however, is not producing one convincing response but sustaining a coherent role through long, changing, and sometimes adversarial interactions. This survey examines recent work on role consistency: the maintenance of identity, character knowledge, expressive style, memory, values, behavioral logic, and safety boundaries over time. We organize the literature around role specification, role-state maintenance, role-aware reasoning, role-consistent alignment, and evaluation.
%U https://aclanthology.org/2026.findings-emnlp.625/
%P 13129-13145

Download as File

Markdown (Informal)

[Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety](https://aclanthology.org/2026.findings-emnlp.625/) (Li et al., Findings 2026)

Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety (Li et al., Findings 2026)

ACL

Chenghao Li, Xueqin Xiao, Yinuo Xiao, Zihan Xu, Xinzhao Li, Yuxuan Luan, Jiwei Wei, Yang Yang, and Chaoning Zhang. 2026. Role Consistency in Role-Playing Agents: A Survey of Evaluation, Memory, Reasoning, Alignment, and Safety. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 13129–13145, Budapest, Hungary. Association for Computational Linguistics.