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.
AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
Fudan University(复旦大学);Rhine AI(莱茵人工智能公司);Shanghai University of Engineering and Science(上海工程技术大学);Xiaohongshu Inc.(小红书公司);Fudan-Aishu Cognitive Intelligence Joint Research Center(复旦-爱数认知智能联合研究中心)
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Southern California(南加州大学);University of Washington(华盛顿大学);Tsinghua University(清华大学);Paradigm Inc.(第四范式公司);University of California, San Diego(加州大学圣地亚哥分校);MosaicML(MosaicML公司)
Interactive Visual Assessment for Text-to-Image Generation Models
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);National Cheng Kung University(成功大学)
Equivalence: An analysis of artists' roles with Image Generative AI from Conceptual Art perspective through an interactive installation design practice
Georgia Institute of Technology(佐治亚理工学院);Delft University of Technology(代尔夫特理工大学);University of California, Santa Barbara(加州大学圣巴巴拉分校)
Intuitive, Interactive Beard and Hair Synthesis with Generative Models
University of Southern California(南加州大学);USC ICT(南加州大学创新技术研究院);Adobe Inc.(奥多比公司);miHoYo(米哈游);ByteDance Research(字节跳动研究院);Tencent America(腾讯美国);Pinscreen Inc.(Pinscreen公司)
PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室);Laboratory of Art and Archaeology Image (Zhejiang University), Ministry of Education(浙江大学艺术与考古图像实验室(教育部));Hong Kong University of Science and Technology(香港科技大学);Zhejiang University(浙江大学)
Artworks Reimagined: Exploring Human-AI Co-Creation through Body Prompting
University of Oulu(奥卢大学);Carleton University(卡尔顿大学);University of Jyväskylä(于韦斯屈莱大学);University of Lisbon(里斯本大学);NOVA FCSH(NOVA 文学院与社会科学学院);IN2PAST(IN2PAST 研究机构)