In this paper titled "Generative Agents: Interactive Simulacra of Human Behavior," authors Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein introduce generative agents as computational software agents that simulate believable human behavior. These generative agents are capable of performing various activities such as waking up, cooking breakfast, going to work, painting, writing, forming opinions, noticing others, initiating conversations and remembering past events and planning for the future. To enable the behavior of these generative agents the authors propose an architecture that extends a large language model. This architecture allows the agent to store a complete record of its experiences using natural language and synthesize those memories over time into higher-level reflections which can be dynamically retrieved by the agent to plan its behavior. The authors instantiate generative agents in an interactive sandbox environment inspired by The Sims video game where users can interact with a small town populated by twenty-five generative agents using natural language commands. Through evaluation it is demonstrated that these generative agents exhibit believable individual and emergent social behaviors such as autonomously spreading invitations for a Valentine's Day party over two days or making new acquaintances and asking each other out on dates for the same event while coordinating their actions to show up together at the right time for the party. The authors further analyze their agent architecture through ablation experiments which demonstrate that observation, planning and reflection are critical components contributing to believability of agent behavior. By combining large language models with computational interactive agents like generative agents described in this work the authors introduce architectural and interaction patterns for creating believable simulations of human behavior with implications for various applications ranging from immersive environments to rehearsal spaces for interpersonal communication and prototyping tools.
Generative agents are computer programs that act like humans and do different tasks. The authors made a plan to make these agents even better by using a special kind of software. This software helps the agents remember things and think about what they should do next. The generative agents live in a pretend town where people can talk to them using words. People who studied the agents found that they act like real individuals and also work together as a group. Experiments showed that watching, planning, and thinking are important for making the agents seem real. Using big computer models along with generative agents can create realistic simulations of how people behave."
Definitions
- Generative: something that creates or produces
- Agents: computer programs or software
- Simulate: imitate or copy something
- Believable: able to be believed or trusted
- Architecture: structure or design of something
- Natural language: words and phrases used in everyday conversation
- Reflections: thoughts or ideas about past experiences
- Ablation experiments: tests where certain parts are removed to see their importance
Generative Agents: Interactive Simulacra of Human Behavior
In this paper titled "Generative Agents: Interactive Simulacra of Human Behavior," authors Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein introduce generative agents as computational software agents that simulate believable human behavior. These generative agents are capable of performing various activities such as waking up, cooking breakfast, going to work, painting, writing, forming opinions, noticing others and initiating conversations while also remembering past events and planning for the future.
Agent Architecture
To enable the behavior of these generative agents the authors propose an architecture that extends a large language model. This architecture allows the agent to store a complete record of its experiences using natural language and synthesize those memories over time into higher-level reflections which can be dynamically retrieved by the agent to plan its behavior.
Interactive Sandbox Environment
The authors instantiate generative agents in an interactive sandbox environment inspired by The Sims video game where users can interact with a small town populated by twenty-five generative agents using natural language commands. Through evaluation it is demonstrated that these generative agents exhibit believable individual and emergent social behaviors such as autonomously spreading invitations for a Valentine's Day party over two days or making new acquaintances and asking each other out on dates for the same event while coordinating their actions to show up together at the right time for the party.
Ablation Experiments
The authors further analyze their agent architecture through ablation experiments which demonstrate that observation, planning and reflection are critical components contributing to believability of agent behavior. By combining large language models with computational interactive agents like generative agents described in this work the authors introduce architectural and interaction patterns for creating believable simulations of human behavior with implications for various applications ranging from immersive environments to rehearsal spaces for interpersonal communication and prototyping tools.
Conclusion
This research paper introduces Generative Agents as computational software capable of simulating believable human behavior through an extended large language model architecture combined with interactive sandbox environments inspired by The Sims video game series allowing users to interact with them using natural language commands resulting in autonomous spread of invitations or coordination between multiple characters exhibiting emergent social behaviors such as asking each other out on dates or showing up together at parties while demonstrating observation planning & reflection are key components contributing towards believability & applicability across immersive environments rehearsal spaces & prototyping tools
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.
