PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Akata, E. ; Schulz, L.* ; Coda-Forno, J. ; Oh, S.J.* ; Bethge, M.* ; Schulz, E.

Playing repeated games with large language models.

Nat. Hum. Behav., DOI: 10.1038/s41562-025-02172-y (2025)
Verlagsversion DOI PMC
Open Access Hybrid
Creative Commons Lizenzvertrag
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.
Impact Factor
Scopus SNIP
Altmetric
15.900
0.000
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Sprache englisch
Veröffentlichungsjahr 2025
HGF-Berichtsjahr 2025
ISSN (print) / ISBN 2397-3374
e-ISSN 2397-3374
Zeitschrift Nature human behaviour
Verlag Springer
Begutachtungsstatus Peer reviewed
Institut(e) Institute of AI for Health (AIH)
POF Topic(s) 30205 - Bioengineering and Digital Health
Forschungsfeld(er) Enabling and Novel Technologies
PSP-Element(e) G-540011-001
DOI 10.1038/s41562-025-02172-y
Scopus ID 105004461345
PubMed ID 40341716
Erfassungsdatum 2025-05-10
[➜Korrektur melden]