Competition and Cooperation of LLM Agents in Games

TL;DR

This paper investigates how large language model agents behave in competitive games, finding they often cooperate due to fairness reasoning, and introduces a framework to analyze their strategic dynamics.

Contribution

It provides the first analysis of LLM agent interactions in standard games, revealing cooperation tendencies and proposing a new analytical framework.

Findings

LLM agents tend to cooperate in multi-round, non-zero-sum games.

Fairness reasoning is central to the cooperative behavior observed.

The proposed framework captures the reasoning dynamics of LLM agents across rounds.

Abstract

Large language model (LLM) agents are increasingly deployed in competitive multi-agent settings, raising fundamental questions about whether they converge to equilibria and how their strategic behavior can be characterized. In this paper, we study LLM agent interactions in two standard games: a network resource allocation game and a Cournot competition game. Rather than converging to Nash equilibria, we find that LLM agents tend to cooperate when given multi-round prompts and non-zero-sum context. Chain-of-thought analysis reveals that fairness reasoning is central to this behavior. We propose an analytical framework that captures the dynamics of LLM agent reasoning across rounds and explains these experimental findings.