Subodh Jena
Blog

Blog

Writing

Life, tech, and everything in-between.

Generative Agents Memory: The Stanford Architecture for Persistent LLM Agents

Apr 22, 2026·8 min·AI

Stanford's Smallville study ran 25 LLM agents that formed relationships and organized events autonomously. The mechanism that made their behavior coherent over days was a three-part memory system: observation, scored retrieval, and periodic reflection.

Work

ExperimentsPortfolio

Connect

AboutContact

© 2026 Subodh Jena

X (Twitter)GitHubLinkedIn