Generative Agents: Interactive Simulacra of Human Behavior
Генеративные агенты: интерактивные симулякры человеческого поведения
2023-10-20
SCID: 54.1/4nd6pkgy
Discuss with AI
generative agentsinteractive sandbox environmentlarge language modelsmemory retrievalsocial behavior simulation
Figures from the paper
Abstract (AI)
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents: computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent’s experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty-five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors. For example, starting with only a single user-specified notion that one agent wants to throw a Valentine’s Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture—observation, planning, and reflection—each contribute critically to the believability of agent behavior. By fusing large language models with computational interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.
Key Findings
1
A sandbox populated by 25 agents supports natural-language interaction and produces believable individual and emergent social behaviors.
2
Ablation results show that observation, planning, and reflection each contribute critically to the believability of agent behavior.
3
From a single goal to host a Valentine’s Day party, agents autonomously disseminate invitations, form acquaintances, arrange dates, and coordinate attendance.
4
The architecture stores agents’ experiences in natural language, synthesizes them into higher-level reflections, and retrieves memories dynamically for planning.
5
The paper introduces generative agents that simulate believable human behavior in interactive environments using large language models.
Research Object
Generative agents (computational software agents that simulate believable human behavior)
Research Subject
the believability of individual and emergent social behaviors, including memory-based planning, reflection, interaction, and coordination
Publication Details
Publication Date
2023-10-20
Journal
Publisher
ISSN
Cited by
2660
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Cited by20
A Survey of Large Language Models2026
A survey on large language model based autonomous agents2024
🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models2025
Generative AI2023
Can Large Language Models Transform Computational Social Science?2023
ExpeL: LLM Agents Are Experiential Learners2024
A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges2024
AgentClinic: a multimodal benchmark for tool-using clinical AI agents2026
Can Generative AI improve social science?2024
When artificial intelligence substitutes humans in higher education: the cost of loneliness, student success, and retention2024
Empowering biomedical discovery with AI agents2024
Visibility into AI Agents2024
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges2025
Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects2026
A review of large language models and autonomous agents in chemistry2024
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review2026
Generative AI Agents With Large Language Model for Satellite Networks via a Mixture of Experts Transmission2024
AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways2025
Human-AI agency in the age of generative AI2025
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent2024