Agents & Tool Use · 2023
Generative Agents: Interactive Simulacra of Human Behavior
Introduced an architecture for believable agents that store experiences in natural language, synthesize memories over time into higher-level reflections, and retrieve them dynamically to plan behavior.
Editorial record
Plain-language summary
Generative agents combine large language models with a memory stream architecture that records experiences, retrieves relevant memories by recency/importance/relevance, reflects to form generalizations, and plans actions recursively. A society of 25 agents in a Sims-like sandbox successfully coordinated complex social behaviors like spreading party invitations and forming relationships, all from a single seed suggestion. This work demonstrated how memory, reflection, and planning enable agents to maintain coherent long-term behavior beyond a single context window.
Source record
Provenance
- Record ID
- P-662
- Record created
- 2026-08-12
- Last reviewed
- 2026-08-12
- Record version
- 1
- https://arxiv.org/abs/2304.03442
- arXiv:2304.03442
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.