Generative agent‐based modeling: an introduction and tutorial

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 to represent human decision‐making in s...

Full description

Saved in:
Bibliographic Details
Published in:System dynamics review 2024-01, Vol.40 (1), p.n/a
Main Authors: Ghaffarzadegan, Navid, Majumdar, Aritra, Williams, Ross, Hosseinichimeh, Niyousha
Format: Article
Language:English
Subjects:
Agent-based models
Dynamic models
Generative artificial intelligence
Large language models
Simulation models
System dynamics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 to represent human decision‐making in social settings. We provide a GABM case in which human behavior can be incorporated into 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 dynamic models of various social systems that include realistic human reasoning and decision‐making. © 2024 System Dynamics Society.
ISSN:0883-7066
1099-1727
DOI:10.1002/sdr.1761