Simulating Ourselves and Our Societies With Generative Agents

Abstract: 

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.

Session Outline:

I will discuss how we build generative agents, and how these agents can be leveraged for real world impact in industry.

Bio: 

Joon Sung Park is a computer science PhD student in the Human-Computer Interaction and Natural Language Processing groups at Stanford University. His work introduces the concept of, and the techniques for creating generative agents -- computational agents that simulate human behavior. His work has won best paper awards at UIST and CHI, as well as multiple best paper nominations and other paper awards at CHI, CSCW, and ASSETS, and has been reported in venues such as The Times, The Guardian, NBC, The New York Times, The New Yorker, Forbes, Wired, Science, and Nature. Joon is recognized with the Microsoft Research Ph.D. Fellowship (2022), Terry Winograd Fellowship (2021), and Siebel Scholar Award (2019).

Open Data Science

 

 

 

Open Data Science
One Broadway
Cambridge, MA 02142
info@odsc.com

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from - Youtube
Vimeo
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google