Cooperation Breakdown in LLM Agents Under Communication Delays

2026-02-12

AI Summary

This study addresses the critical yet underexplored impact of real-world communication delays on cooperative behavior in large language model (LLM) multi-agent systems. The authors propose FLCOA, a five-layer cooperative analysis framework, and integrate it with continuous prisoner’s dilemma simulations incorporating communication latency. Their findings reveal, for the first time, a U-shaped relationship between delay magnitude and cooperation levels among LLM agents: moderate delays encourage exploitative strategies, whereas excessively high delays paradoxically suppress exploitation and foster reciprocal cooperation. This work underscores the profound influence of low-level resource constraints—particularly timing limitations—on emergent multi-agent collaboration, offering both theoretical grounding and practical design principles for developing robust LLM-based multi-agent systems.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• LLM-based multi-agent systems
• cooperation breakdown
• communication delay
• coordination
• resource constraints

Innovation

• communication delay
• LLM-based multi-agent systems
• cooperation breakdown
• FLCOA framework
• Continuous Prisoner's Dilemma