Cooperation Breakdown in LLM Agents Under Communication Delays

TL;DR

This paper investigates how communication delays affect cooperation among LLM-based multi-agent systems, revealing a U-shaped relationship where moderate delays can both harm and promote cooperation.

Contribution

It introduces the FLCOA framework for understanding cooperation in autonomous agents and demonstrates the impact of communication delays through novel simulations.

Findings

Increased delays lead to exploitation behaviors in agents.

Moderate delays can reduce cooperation, but excessive delays may restore cooperation.

Communication delay has a significant impact on multi-agent system dynamics.

Abstract

LLM-based multi-agent systems (LLM-MAS), in which autonomous AI agents cooperate to solve tasks, are gaining increasing attention. For such systems to be deployed in society, agents must be able to establish cooperation and coordination under real-world computational and communication constraints. We propose the FLCOA framework (Five Layers for Cooperation/Coordination among Autonomous Agents) to conceptualize how cooperation and coordination emerge in groups of autonomous agents, and highlight that the influence of lower-layer factors - especially computational and communication resources - has been largely overlooked. To examine the effect of communication delay, we introduce a Continuous Prisoner's Dilemma with Communication Delay and conduct simulations with LLM-based agents. As delay increases, agents begin to exploit slower responses even without explicit instructions. Interestingly, excessive delay reduces cycles of exploitation, yielding a U-shaped relationship between delay magnitude and mutual cooperation. These results suggest that fostering cooperation requires attention not only to high-level institutional design but also to lower-layer factors such as communication delay and resource allocation, pointing to new directions for MAS research.