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.

翻译：大语言模型的最新进展显著推动了角色扮演语言体（RPLAs）的兴起，即专门用于模拟指定角色的AI系统。通过利用大语言模型的多种高级能力，包括情境学习、指令遵循和社交智能，RPLAs实现了显著的人类逼真感和生动的角色扮演表现。RPLAs能够模拟广泛角色，涵盖历史人物、虚构角色乃至现实个体。因此，它们催生了众多AI应用，如情感陪伴、交互式视频游戏、个性化助手与副驾驶，以及数字克隆。本文对该领域进行了全面综述，阐明了RPLAs与前沿大语言模型技术融合的演进历程与最新进展。我们将角色划分为三类：1）统计刻板印象驱动的统计人口属性角色；2）专注于既定形象的固定角色角色；3）通过持续用户交互定制以提供个性化服务的个性化角色。我们首先呈现RPLAs当前方法的全面概述，随后详述每种角色类型对应的数据来源、智能体构建与评估细节。接着，我们讨论RPLAs的基本风险、现有局限及未来前景。此外，我们简要回顾了RPLAs在AI应用中的实践，这反映了塑造并推动RPLA研究的实际用户需求。通过本文，我们旨在建立RPLA研究与应用清晰的分类体系，促进这一关键且持续演进领域的未来研究，并为人类与RPLAs和谐共存的未来铺平道路。