Saved in:
Bibliographic Details
Main Authors: Shi, Wenlong, Lian, Jianxun, Wu, Mingqi, Qin, Haiming, Zhou, Mingyang, Xie, Xing, Chao, Naipeng, Liao, Hao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17044
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913135155216384
author Shi, Wenlong
Lian, Jianxun
Wu, Mingqi
Qin, Haiming
Zhou, Mingyang
Xie, Xing
Chao, Naipeng
Liao, Hao
author_facet Shi, Wenlong
Lian, Jianxun
Wu, Mingqi
Qin, Haiming
Zhou, Mingyang
Xie, Xing
Chao, Naipeng
Liao, Hao
contents Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, particularly in realistic social scenarios. Existing research predominantly focuses on character-level settings and relies on static evaluation formats, failing to capture the complexity of everyday social interactions. In this work, we present PersonaArena, a dynamic simulation framework for evaluating and improving persona-level role-playing in LLMs. PersonaArena leverages a large, filtered corpus of user-generated social content to construct a nuanced persona bank, and elicits multi-turn, context-rich interactions within simulated social environments. Our framework features a multi-agent debating judge for holistic and unbiased assessment. Through extensive experiments, we demonstrate that PersonaArena enables rigorous evaluation and enhancement of LLMs' role-playing capabilities, advancing the development of more authentic and socially adept AI agents.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17044
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models
Shi, Wenlong
Lian, Jianxun
Wu, Mingqi
Qin, Haiming
Zhou, Mingyang
Xie, Xing
Chao, Naipeng
Liao, Hao
Artificial Intelligence
Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, particularly in realistic social scenarios. Existing research predominantly focuses on character-level settings and relies on static evaluation formats, failing to capture the complexity of everyday social interactions. In this work, we present PersonaArena, a dynamic simulation framework for evaluating and improving persona-level role-playing in LLMs. PersonaArena leverages a large, filtered corpus of user-generated social content to construct a nuanced persona bank, and elicits multi-turn, context-rich interactions within simulated social environments. Our framework features a multi-agent debating judge for holistic and unbiased assessment. Through extensive experiments, we demonstrate that PersonaArena enables rigorous evaluation and enhancement of LLMs' role-playing capabilities, advancing the development of more authentic and socially adept AI agents.
title PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2605.17044