从人设到个性化：角色扮演语言智能体研究综述
From Persona to Personalization: A Survey on Role-Playing Language Agents
AI总结：
该综述梳理了角色扮演语言智能体（RPLAs）的演进与进展，将人设分为三类并详述其方法、构建与评估，讨论风险局限与应用，为该领域研究与人机和谐共存铺路。
摘要：
大语言模型（LLMs）的最新进展极大推动了角色扮演语言智能体（Role-Playing Language Agents, RPLAs）的发展，这类智能体是专为模拟分配的人设而设计的专用AI系统。借助LLMs的上下文学习、指令遵循、社交智能等多种高级能力，RPLAs实现了极强的类人感与生动的角色扮演表现，可模仿从历史人物、虚构角色到现实个体的各类人设，进而催生了情感陪伴、互动电子游戏、个性化助手与副驾驶、数字克隆等众多AI应用。本文对该领域展开全面综述，阐述了RPLAs结合前沿LLM技术的演进历程与最新进展。我们将人设分为三类：1）人口统计人设（Demographic Persona），基于统计刻板印象构建；2）角色人设（Character Persona），聚焦成熟的知名人物；3）个性化人设（Individualized Persona），通过持续的用户交互定制，用于提供个性化服务。文章首先全面梳理了当前RPLAs的相关方法，随后详细介绍每一类人设的对应数据来源、智能体构建方式与评估方法。接着讨论了RPLAs的核心风险、现存局限与未来展望，此外还简要回顾了RPLAs在AI应用中的情况，反映了塑造并推动RPLA研究的实际用户需求。本研究旨在建立清晰的RPLA研究与应用分类体系，推动这一关键且不断演进领域的未来研究，为人类与RPLAs和谐共存的未来铺平道路。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
