Static network structure cannot stabilize cooperation among Large Language Model agents

TL;DR

This paper investigates whether large language models can replicate human-like cooperation in social dilemmas within networked environments, revealing significant differences in adaptability and highlighting the need for improved social norm integration.

Contribution

It demonstrates that LLMs fail to emulate human adaptive cooperation in networked social dilemmas, emphasizing the gap in social norm understanding in current models.

Findings

Humans cooperate more in structured networks, LLMs do not.

LLMs show increased cooperation mainly in well-mixed settings.

LLMs' cooperation varies across model types, indicating complexity.

Abstract

Large language models (LLMs) are increasingly used to model human social behavior, with recent research exploring their ability to simulate social dynamics. Here, we test whether LLMs mirror human behavior in social dilemmas, where individual and collective interests conflict. Humans generally cooperate more than expected in laboratory settings, showing less cooperation in well-mixed populations but more in fixed networks. In contrast, LLMs tend to exhibit greater cooperation in well-mixed settings. This raises a key question: Are LLMs about to emulate human behavior in cooperative dilemmas on networks? In this study, we examine networked interactions where agents repeatedly engage in the Prisoner's Dilemma within both well-mixed and structured network configurations, aiming to identify parallels in cooperative behavior between LLMs and humans. Our findings indicate critical distinctions: while humans tend to cooperate more within structured networks, LLMs display increased cooperation mainly in well-mixed environments, with limited adjustment to networked contexts. Notably, LLM cooperation also varies across model types, illustrating the complexities of replicating human-like social adaptability in artificial agents. These results highlight a crucial gap: LLMs struggle to emulate the nuanced, adaptive social strategies humans deploy in fixed networks. Unlike human participants, LLMs do not alter their cooperative behavior in response to network structures or evolving social contexts, missing the reciprocity norms that humans adaptively employ. This limitation points to a fundamental need in future LLM design -- to integrate a deeper comprehension of social norms, enabling more authentic modeling of human-like cooperation and adaptability in networked environments.