Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.
翻译:可信的人类行为代理可以增强从沉浸式环境到人际交流排练空间到原型制作工具等交互应用。在本文中,我们介绍生成代理人——计算机软件代理,模拟可信的人类行为。生成代理人早上醒来、做饭、上班;艺术家绘画,作家写作;他们形成观点,注意到彼此,开始交谈;他们回忆和反思过去的日子,计划下一天。为了启用生成代理人,我们描述了一个架构,将大型语言模型扩展到使用自然语言存储代理人经历的完整记录,随着时间综合这些记忆到更高的反思层面,并动态检索它们以规划行为。我们通过实例化生成代理人来填充一个灵感来自The Sims的交互式沙箱环境,最多可以有二十五个代理人使用自然语言与最终用户进行交互。在评估中,这些生成代理人产生可信的个体和紧急的社交行为:例如,从只有一个用户指定的想法开始,即一个代理人想举办情人节派对,代理人在接下来的两天内自主传播派对邀请,结交新朋友,相约派对约会,并协调在正确的时刻一起出现在派对上。我们通过去除试验表明我们代理人体系结构的观察、规划和反思组件分别对代理人行为的可信度做出了重要贡献。通过将大型语言模型与计算机交互代理融合,这项工作引入了启用人类行为可信模拟的体系结构和交互模式。