Simulating Market Equilibrium with Large Language Models

Simple item page
dc.contributor.authorJunqué De Fortuny, Enric
dc.date.accessioned2024-12-26T21:08:43Z
dc.date.available2024-12-26T21:08:43Z
dc.date.issued2025-01-07
dc.description.abstractLarge Language Models (LLMs) have the potential to simulate complex human decision-making and economic behavior, making them well-suited for training simulations. This study explores LLMs' ability to simulate a market equilibrium game commonly used in MBA classrooms to train future business leaders. We test three simulation architectures: prompt-based, Retrieval Augmented Generation-based, and controller-based. The prompt-based approach struggled with limited context, while the RAG-based system improved information retrieval but occasionally veered off course. To address these challenges, we developed a controller-based simulation integrating multiple LLM agents and custom tools, which enhanced both control and accuracy. Our results show that this approach not only improves the fidelity of economic simulation, but also enriches the learning experience for students by providing more accurate, engaging, and realistic business case environments.
dc.format.extent8
dc.identifier.doi10.24251/HICSS.2025.599
dc.identifier.isbn978-0-9981331-8-8
dc.identifier.other2a03df98-73fe-49aa-a357-76a0d727aaaa
dc.identifier.urihttps://hdl.handle.net/10125/109446
dc.relation.ispartofProceedings of the 58th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectGenerative Artificial Intelligence in Higher Education
dc.subjectcontroller, education, llm, rag, rpg
dc.titleSimulating Market Equilibrium with Large Language Models
dc.typeConference Paper
dc.type.dcmiText
prism.startingpage4976

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0488.pdf
Size:
529.75 KB
Format:
Adobe Portable Document Format
Download

Collections

Generative Artificial Intelligence in Higher Education