🚀NEW LABGetting Started with Claude AgentsStart lab
Agents

Generative Agents: Interactive Simulacra of Human Behavior

First page
Generative Agents: Interactive Simulacra of Human Behavior
Paper summary

Stanford/Google's landmark paper on LLM-powered social simulations.

Ask this paper

Key points
01

"Smallville" simulation: Creates a town of 25 LLM-powered agents who plan their days, remember experiences, form relationships, and even organize parties.

02

Memory-reflection-planning: Combines a complete memory stream, synthesized reflections, and dynamic planning to create emergent social behavior.

03

Emergent social dynamics: Agents exhibit emergent phenomena like information diffusion, relationship formation, and coordinated planning.

04

Agent research foundation: One of the most influential 2023 agent papers, sparking the explosion of LLM agent simulation work including AutoGPT, BabyAGI, and CAMEL.

Every Monday
Get next week’s papers.
Subscribe on Substack