Game-theory behaviour of large language models: The case of Keynesian beauty contests

Lu Siting Estee ()
Additional contact information
Lu Siting Estee: School of Economics, University of Edinburgh – 30 Buccleuch Pl, Edinburgh EH8 9JT, United Kingdom

Economics and Business Review, 2025, vol. 11, issue 2, 119-148

Abstract: The growing adoption of large language models (LLMs) presents potential for deeper understanding of human behaviours within game theory frameworks. This paper examines strategic interactions among multiple types of LLM-based agents in a classical beauty contest game. LLM-based agents demonstrate varying depth of reasoning that fall within a range of level-0 to 1, which are lower than experimental results conducted with human subjects in previous studies. However, they do display a similar convergence pattern towards Nash Equilibrium choice in repeated settings. Through simulations that vary the group composition of agent types, I found that environments with a lower strategic uncertainty enhance convergence for LLM-based agents, and environments with mixed strategic types accelerate convergence for all. Results with simulated agents not only convey insights into potential human behaviours in competitive settings, but also prove valuable for understanding strategic interactions among algorithms.

Keywords: large language models; economic games; strategic interactions (search for similar items in EconPapers)
JEL-codes: C63 C70 C90 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.18559/ebr.2025.2.2182 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:vrs:ecobur:v:11:y:2025:i:2:p:119-148:n:1005

DOI: 10.18559/ebr.2025.2.2182

Access Statistics for this article

Economics and Business Review is currently edited by Tadeusz Kowalski

More articles in Economics and Business Review from Sciendo
Bibliographic data for series maintained by Peter Golla ().