Playing repeated games with large language models

Elif Akata (), Lion Schulz, Julian Coda-Forno, Seong Joon Oh, Matthias Bethge and Eric Schulz
Additional contact information
Elif Akata: Helmholtz Munich
Lion Schulz: Max Planck Institute for Biological Cybernetics
Julian Coda-Forno: Helmholtz Munich
Seong Joon Oh: University of Tübingen
Matthias Bethge: University of Tübingen
Eric Schulz: Helmholtz Munich

Nature Human Behaviour, 2025, vol. 9, issue 7, 1380-1390

Abstract: Abstract Large language models (LLMs) are increasingly used in applications where they interact with humans and other agents. We propose to use behavioural game theory to study LLMs’ cooperation and coordination behaviour. Here we let different LLMs play finitely repeated 2 × 2 games with each other, with human-like strategies, and actual human players. Our results show that LLMs perform particularly well at self-interested games such as the iterated Prisoner’s Dilemma family. However, they behave suboptimally in games that require coordination, such as the Battle of the Sexes. We verify that these behavioural signatures are stable across robustness checks. We also show how GPT-4’s behaviour can be modulated by providing additional information about its opponent and by using a ‘social chain-of-thought’ strategy. This also leads to better scores and more successful coordination when interacting with human players. These results enrich our understanding of LLMs’ social behaviour and pave the way for a behavioural game theory for machines.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41562-025-02172-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:nat:nathum:v:9:y:2025:i:7:d:10.1038_s41562-025-02172-y

Ordering information: This journal article can be ordered from
https://www.nature.com/nathumbehav/

DOI: 10.1038/s41562-025-02172-y

Access Statistics for this article

Nature Human Behaviour is currently edited by Stavroula Kousta

More articles in Nature Human Behaviour from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().