Generative agent‐based modeling: an introduction and tutorial
System Dynamics Review · 2024-01 · 40 (1)
DOI: 10.1002/sdr.1761 ↗Kurz gefasst
Fachartikel in der Zeitschrift System Dynamics Review, online erschienen am 10.01.2024. Verfasst von Navid Ghaffarzadegan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 69-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science Foundation.
Abstract (Originalsprache)
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 The Author(s). System Dynamics Review published by John Wiley & Sons Ltd on behalf of System Dynamics Society.
Förderung
- National Science Foundation
Zitieren
APA
Ghaffarzadegan, N., Majumdar, A., Williams, R., & Hosseinichimeh, N. (2024). Generative agent‐based modeling: an introduction and tutorial. System Dynamics Review, 40(1). https://doi.org/10.1002/sdr.1761
Vancouver
Ghaffarzadegan N, Majumdar A, Williams R, Hosseinichimeh N. Generative agent‐based modeling: an introduction and tutorial. System Dynamics Review. 2024;40(1). doi:10.1002/sdr.1761
BibTeX
@article{Ghaffarzadegan2024,
author = {Ghaffarzadegan, Navid and Majumdar, Aritra and Williams, Ross and Hosseinichimeh, Niyousha},
title = {Generative agent‐based modeling: an introduction and tutorial},
journal = {System Dynamics Review},
year = {2024},
volume = {40},
number = {1},
doi = {10.1002/sdr.1761}
}
EUVIMED