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.
Abstract (translated)
近年来，大型语言模型（LLMs）的进步显著推动了角色扮演语言代理（RPLAs）的发展，即专门设计来模拟分配角色的AI系统。通过利用LLMs的多项先进能力，包括上下文学习、指令跟随和社会智能，RPLAs实现了惊人的人性相似度和生动的角色扮演表现。RPLAs可以模拟各种角色，从历史人物和虚构角色到现实生活中的人。因此，它们推动了 numerous AI应用的发展，如情感伴侣、交互式视频游戏、私人助手和副驾驶，以及数字克隆。在本文中，我们对这个领域进行了全面的调查，展示了RPLAs与尖端LLM技术相结合的演变和最近进展。我们将角色归类为三种类型：1） demographic persona，利用统计刻板印象；2） established persona，关注已知人物；3） personalized persona，通过持续的用户交互进行个性化定制服务。我们首先对RPLAs的当前方法进行全面概述，然后对每种角色类型的详细介绍，涵盖相应数据来源、代理构建和评估。接着，我们讨论了RPLAs的基本风险、现有局限性和未来前景。此外，我们还简要回顾了RPLAs在AI应用中的情况，反映了实际用户需求对RPLA研究的影响。通过这项工作，我们旨在建立一个清晰的RPLA研究范畴和应用，促进在这个关键且不断发展的领域进行未来的研究，为人类和RPLA和谐共存铺平道路。
URL
https://arxiv.org/abs/2404.18231
