@inproceedings{chen-etal-2025-towards-design,
title = "Towards a Design Guideline for {RPA} Evaluation: A Survey of Large Language Model-Based Role-Playing Agents",
author = "Chen, Chaoran and
Yao, Bingsheng and
Zou, Ruishi and
Hua, Wenyue and
Lyu, Weimin and
Li, Toby Jia-Jun and
Wang, Dakuo",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.938/",
doi = "10.18653/v1/2025.findings-acl.938",
pages = "18229--18268",
ISBN = "979-8-89176-256-5",
abstract = "Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. However, evaluating RPAs is challenging due to diverse task requirements and agent designs.This paper proposes an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024.Our analysis identifies six agent attributes, seven task attributes, and seven evaluation metrics from existing literature.Based on these findings, we present an RPA evaluation design guideline to help researchers develop more systematic and consistent evaluation methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-towards-design">
<titleInfo>
<title>Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaoran</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingsheng</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruishi</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyue</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weimin</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toby</namePart>
<namePart type="given">Jia-Jun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dakuo</namePart>
<namePart type="family">Wang</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>Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. However, evaluating RPAs is challenging due to diverse task requirements and agent designs.This paper proposes an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024.Our analysis identifies six agent attributes, seven task attributes, and seven evaluation metrics from existing literature.Based on these findings, we present an RPA evaluation design guideline to help researchers develop more systematic and consistent evaluation methods.</abstract>
<identifier type="citekey">chen-etal-2025-towards-design</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.938</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.938/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>18229</start>
<end>18268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents
%A Chen, Chaoran
%A Yao, Bingsheng
%A Zou, Ruishi
%A Hua, Wenyue
%A Lyu, Weimin
%A Li, Toby Jia-Jun
%A Wang, Dakuo
%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 chen-etal-2025-towards-design
%X Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. However, evaluating RPAs is challenging due to diverse task requirements and agent designs.This paper proposes an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024.Our analysis identifies six agent attributes, seven task attributes, and seven evaluation metrics from existing literature.Based on these findings, we present an RPA evaluation design guideline to help researchers develop more systematic and consistent evaluation methods.
%R 10.18653/v1/2025.findings-acl.938
%U https://aclanthology.org/2025.findings-acl.938/
%U https://doi.org/10.18653/v1/2025.findings-acl.938
%P 18229-18268
Markdown (Informal)
[Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents](https://aclanthology.org/2025.findings-acl.938/) (Chen et al., Findings 2025)
ACL