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赋能多种交互应用，从沉浸式环境到人际沟通的演练空间，再到原型设计工具。本文提出生成式智能体——模拟可信人类行为的计算软件代理。这些生成式智能体能够起床、做早餐、上班；画家作画，作家写作；它们形成观点、相互观察并展开对话；它们会回忆和反思过往经历，同时规划第二天的行动。为了实现生成式智能体，我们提出一种架构，该架构扩展了大语言模型，能够使用自然语言存储智能体经历的全记录，随时间将这些记忆合成为更高层次的反思，并动态检索以规划行为。我们实例化生成式智能体，填充一个受《模拟人生》启发的交互式沙盒环境，终端用户可通过自然语言与包含二十五个智能体的小镇互动。评估表明，这些生成式智能体能产生可信的个体及涌现性社会行为：例如，仅从一个智能体想要举办情人节派对这一用户指定概念出发，智能体在未来两天自主传播派对邀请、结识新朋友、互相邀约约会，并协调准时共同出席派对。通过消融实验证明，我们智能体架构的组成部分——观察、规划和反思——各自对智能体行为的可信度具有关键贡献。通过将大语言模型与计算型交互智能体融合，本工作引入了实现人类行为可信模拟的架构与交互模式。