HomeResearch LibraryGenerative Agents: Interactive Simulacra of Human Behav…
system architectureChapter 2UIST 2023 · 2023

Generative Agents: Interactive Simulacra of Human Behavior

Joon Sung Park (Stanford), Joseph C. O'Brien (Stanford), Carrie J. Cai (Google Research)

Abstract

We introduce generative agents, computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists create new paintings; and friends throw birthday parties.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

The memory stream architecture in this paper is one of the most practically useful contributions to enterprise agent design. The three-tier memory (observation → reflection → planning) maps directly onto what enterprise agents need for sustained operation.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Key Contributions

  • →Memory stream architecture
  • →Reflection mechanism for high-level synthesis
  • →Planning from observations

Topics

multi-agent simulationmemory architectureagent behaviorlong-horizon planning