[2304.03442] Generative Agents: Interactive Simulacra of Human Behavior
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.
# link_tq049w6ts2.pdf ## Metadata - PDFFormatVersion=1.5 - Language=en - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20230808002435Z - Creator=LaTeX with hyperref - ModDate=D:20230808002435Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Producer=pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Trapped=False - pdfaextension:schemas=Adobe PDF Schemapdfhttp://ns.adobe.com/pdf/1.3/TrappedTextinternalIndica
saved by
- Eric Chang
- Bryan Chiang
- Falah Rajput
- Svitlana Midianko
- brunella k
- Rajan Agarwal
- Anna Wang
- Linda
- Julian Quevedo
- Aryan Naik
- Jacky Huang
- Ben Brooks
related reading
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Generative Agents: Stanford's Groundbreaking AI Study Simulates Authentic Human Behavior - Artisanaartisana.ai
- Generative Agent Simulations of 1,000 Peopleantephase.com
- Simulating human behavior | Similesimile.com
- [2411.00114] Project Sid: Many-agent simulations toward AI civilizationarxiv.org
- Building Effective AI Agents \ Anthropicanthropic.com
- Building reliable AI agents · parth sareenparthsareen.com
- Cyborgism — LessWronglesswrong.com
- Today, we are releasing a research preview of our user model, along with a set of evaluations designed to measure how faithfully user models capture human behavior.persimmon.humansand.ai
- Building Effective AI Agents \ Anthropicanthropic.com
- Genie: Generative Interactive Environmentsdeepmind.google