Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence

TL;DR

This paper explores the integration of large language models with mechanistic social models to create Generative Agent-Based Models (GABMs) that simulate human decision-making and social norm diffusion.

Contribution

It introduces a novel framework coupling mechanistic models with generative AI, demonstrating its application in simulating social norm diffusion within organizations.

Findings

GABMs can effectively incorporate realistic human reasoning.

Sensitivity of social diffusion outcomes to prompt variations.

The simple model serves as a guide for future complex social simulations.

Abstract

We discuss the emerging new opportunity for building feedback-rich computational models of social systems using generative artificial intelligence. Referred to as Generative Agent-Based Models (GABMs), such individual-level models utilize large language models such as ChatGPT to represent human decision-making in social settings. We provide a GABM case in which human behavior can be incorporated in simulation models by coupling a mechanistic model of human interactions with a pre-trained large language model. This is achieved by introducing a simple GABM of social norm diffusion in an organization. For educational purposes, the model is intentionally kept simple. We examine a wide range of scenarios and the sensitivity of the results to several changes in the prompt. We hope the article and the model serve as a guide for building useful diffusion models that include realistic human reasoning and decision-making.