Generative Agents: Interactive Simulacra of Human Behavior

By Joon Sung Park, Joseph O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein. ACM Symposium on User Interface Software and Technology, 2023

4,832 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Social Psychology

View Paper: https://www.semanticscholar.org/paper/5278a8eb2ba2429d4029745caf4e661080073c81

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Social Psychology

Citations in the corpus

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (2023, background): “, 2023) and it can be used to simulate agentic behavior (Wang et al., 2023a; Park et al., 2023; Wu et al., 2023).”
Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf (2023, background): “Furthermore, studies have shown that LLMs exhibit a certain degree of theory of mind capabilities (Bubeck et al., 2023; Shapira et al., 2023; Kosinski, 2023), as well as the potential to simulate believable human behaviors (Park et al., 2023).”
Building Cooperative Embodied Agents Modularly with Large Language Models (2023, background): “More recently, Park et al. (2023) built an agent society using LLMs augmented with memories to simulate human behavior.”
Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents (2023, background): “One such multi-agent system can be seen in the work of [2], who introduced generative agents that imitate plausible human behavior within an interactive sandbox environment.”
Voyager: An Open-Ended Embodied Agent with Large Language Models (2023, background): “Decision-making Agents in Minecraft.”
Prompt Injection attack against LLM-integrated Applications (2023, background): “Another instance is Generative Agents [43] which is LLMbacked interative software to simulate human behaviors.”
Executable Code Actions Elicit Better LLM Agents (2024, background): “We inquire: how to effectively expand LLM agents’ action space for solving complex real-world problems?”
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025, neutral): “…serve to not only reinforce the structural differences between Generative AI, AI Agents, and Agentic AI(as explained in Table 4), but also introduce an emergent category of Generative Agents representing modular agents designed for embedded subtask-level generation within broader workflows [154].”
ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback (2023, neutral): “With more powerful backbone models, we believe U LTRA F EEDBACK will greatly benefit autonomous agents (Park et al., 2023; Qin et al., 2023; Qian et al., 2023) and feedback learning (Yao et al., 2023; Shinn et al., 2023) research.”
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025, neutral): “…for next-generation large language models, driven by diverse real-world applications ranging from in-depth reasoning (DeepSeek-AI, 2025; Zelik-man et al., 2022), repository-level code generation (Zhang et al., 2023a; Zhang et al.) and multi-turn autonomous agent systems (Park et al., 2023).”
ExpeL: LLM Agents Are Experiential Learners (2023, background): “Other agents exhibit potential in persistent memory within multi-agent contexts (Park et al. 2023; Maas et al. 2023).”
VideoAgent: Long-form Video Understanding with Large Language Model as Agent (2024, positive): “Advances in large language models (LLMs), especially their emerging reasoning and planning capabilities [52, 62, 70], has inspired recent research in natural language processing to leverage them as agents in real-world scenarios [35, 63].”
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations (2023, background): “Large language models (LLMs) have demonstrated remarkable capabilities across various tasks (Park et al., 2023; Kaddour et al., 2023; Song et al.; Li et al., 2023a; Wang et al., 2023a; Chen et al., 2023; Zheng et al., 2023; Wang et al., 2023c), However, even the most advanced LLMs face challenges…”
Large Language Models as Analogical Reasoners (2023, background): “…with more structured algorithms and search methods (Khot et al., 2022; Drozdov et al., 2022; Zelikman et al., 2022; Yao et al., 2023; Press et al., 2022; Khattab et al., 2022; Jung et al., 2022), as well as longer-horizon action and planning (Yao et al., 2022; Hao et al., 2023; Park et al., 2023).”
The rise and potential of large language model based agents: a survey (2025, positive): “However, these eﬀorts have predominantly focused on enhancing speciﬁc skills (such as symbolic reasoning or quick responsiveness) or mastering particular tasks (such as Go or Chess) [13–15].”
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (2023, background): “…Learning (ICL) (Min et al., 2022; Dong et al., 2023), Retrieval Augment Generation (RAG) (Lewis et al., 2020; Asai et al., 2024), and Multi-turn Agent (Shen et al., 2024; Park et al., 2023; Wu et al., 2023a) are driving prompts to be increasingly longer, even reaching thousands of to-kens.”