Generative Agent Simulations of 1,000 People

N/A

Generative Agent Simulations of 1,000 People Authors: Joon Sung Park1*, Carolyn Q. Zou1,2, Aaron Shaw2, Benjamin Mako Hill3, Carrie Cai4, Meredith Ringel Morris5, Robb Willer6, Percy Liang1, Michael S. Bernstein1 Affiliations: 1 Computer Science Department, Stanford University; Stanford, CA, 94305, USA. 2 Department of Communication Studies, Northwestern University; Evanston, IL, 60208, USA. 3 Department of Communication, University of Washington; Seattle, WA 98195, USA. 4 Google DeepMind; Mountain View, CA 94043, USA. 5 Google DeepMind;…

saved by

• Anthea Tawiah

related reading

• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• Generative Agents: Stanford's Groundbreaking AI Study Simulates Authentic Human Behavior - Artisanaartisana.ai
• [2608.19549] Generating Diverse Personas for User Simulators to Test Interview Dialogue Systemsarxiv.org
• [2411.00114] Project Sid: Many-agent simulations toward AI civilizationarxiv.org
• Simulating the World with 8.3 Billion Persona Agentsarxiv.org
• Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluationsarxiv.org
• 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
• Evaluating LLMs for Impersonationarxiv.org
• Quantifying the Utility of User Simulators for Building Collaborative LLM Assistantsarxiv.org
• [2508.19227] Generative Interfaces for Language Modelsarxiv.org