Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Persona to Personalization: A Survey on Role-Playing Language Agents

Jiangjie Chen, Xintao Wang, Rui Xu, Siyu Yuan, Yikai Zhang, Wei Shi, Jian Xie, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, Yanghua Xiao

TL;DR

<3-5 sentence high-level summary>This survey analyzes role-playing language agents (RPLAs) built on large language models, proposing a three-way taxonomy of personas: Demographic, Character, and Individualized. It reviews foundational LLM capabilities and agent architectures, including planning, tool usage, and memory modules, that enable realistic, interactive personas. It contrasts parametric training with nonparametric prompting for constructing RPLAs, and details evaluation methods for both general role-playing ability and persona fidelity, while foregrounding risks such as toxicity, bias, hallucination, and privacy. The work also surveys data sources, deployment challenges, and real-world products, offering a roadmap for safe, personalized, and scalable RPLA research and applications.

Abstract

Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate assigned personas. By harnessing multiple advanced abilities of LLMs, including in-context learning, instruction following, and social intelligence, RPLAs achieve a remarkable sense of human likeness and vivid role-playing performance. RPLAs can mimic a wide range of personas, ranging from historical figures and fictional characters to real-life individuals. Consequently, they have catalyzed numerous AI applications, such as emotional companions, interactive video games, personalized assistants and copilots, and digital clones. In this paper, we conduct a comprehensive survey of this field, illustrating the evolution and recent progress in RPLAs integrating with cutting-edge LLM technologies. We categorize personas into three types: 1) Demographic Persona, which leverages statistical stereotypes; 2) Character Persona, focused on well-established figures; and 3) Individualized Persona, customized through ongoing user interactions for personalized services. We begin by presenting a comprehensive overview of current methodologies for RPLAs, followed by the details for each persona type, covering corresponding data sourcing, agent construction, and evaluation. Afterward, we discuss the fundamental risks, existing limitations, and future prospects of RPLAs. Additionally, we provide a brief review of RPLAs in AI applications, which reflects practical user demands that shape and drive RPLA research. Through this work, we aim to establish a clear taxonomy of RPLA research and applications, and facilitate future research in this critical and ever-evolving field, and pave the way for a future where humans and RPLAs coexist in harmony.

From Persona to Personalization: A Survey on Role-Playing Language Agents

TL;DR

<3-5 sentence high-level summary>This survey analyzes role-playing language agents (RPLAs) built on large language models, proposing a three-way taxonomy of personas: Demographic, Character, and Individualized. It reviews foundational LLM capabilities and agent architectures, including planning, tool usage, and memory modules, that enable realistic, interactive personas. It contrasts parametric training with nonparametric prompting for constructing RPLAs, and details evaluation methods for both general role-playing ability and persona fidelity, while foregrounding risks such as toxicity, bias, hallucination, and privacy. The work also surveys data sources, deployment challenges, and real-world products, offering a roadmap for safe, personalized, and scalable RPLA research and applications.

Abstract

Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate assigned personas. By harnessing multiple advanced abilities of LLMs, including in-context learning, instruction following, and social intelligence, RPLAs achieve a remarkable sense of human likeness and vivid role-playing performance. RPLAs can mimic a wide range of personas, ranging from historical figures and fictional characters to real-life individuals. Consequently, they have catalyzed numerous AI applications, such as emotional companions, interactive video games, personalized assistants and copilots, and digital clones. In this paper, we conduct a comprehensive survey of this field, illustrating the evolution and recent progress in RPLAs integrating with cutting-edge LLM technologies. We categorize personas into three types: 1) Demographic Persona, which leverages statistical stereotypes; 2) Character Persona, focused on well-established figures; and 3) Individualized Persona, customized through ongoing user interactions for personalized services. We begin by presenting a comprehensive overview of current methodologies for RPLAs, followed by the details for each persona type, covering corresponding data sourcing, agent construction, and evaluation. Afterward, we discuss the fundamental risks, existing limitations, and future prospects of RPLAs. Additionally, we provide a brief review of RPLAs in AI applications, which reflects practical user demands that shape and drive RPLA research. Through this work, we aim to establish a clear taxonomy of RPLA research and applications, and facilitate future research in this critical and ever-evolving field, and pave the way for a future where humans and RPLAs coexist in harmony.
Paper Structure (86 sections, 2 figures, 4 tables)

This paper contains 86 sections, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Preliminary
  3. The Roadmap of Large Language Models
  4. Emerged Abilities in LLMs
  5. Anthropomorphic Cognition in LLMs
  6. Retrieval-augmented Generation of LLMs
  7. LLM-powered Language Agents
  8. Planning Module
  9. Tool-usage Module
  10. Memory Mechanism
  11. Overview of RPLAs
  12. RPLA Definition
  13. RPLA Construction
  14. RPLA Evaluation
  15. Demographic Persona
  16. ...and 71 more sections

Figures (2)

  • Figure 1: An overview of various persona types for RPLAs. In this survey, we categorize personas into three types: 1) Demographic Persona, 2) Character Persona, and 3) Individualized Persona. We showcase their definition, data sources, examples, use cases and corresponding applications.
  • Figure 2: Taxonomy of representative recent research on RPLAs.