在通信延迟下LLM代理间的合作破裂
Cooperation Breakdown in LLM Agents Under Communication Delays
AI总结：
研究探讨了通信延迟对LLM多智能体系统中合作的影响，发现延迟增加会引发代理剥削行为，但过度延迟反而促进合作，揭示了低层因素对合作的重要性。
摘要：
基于大型语言模型的多智能体系统（LLM-MAS）中，自主AI代理通过合作解决任务，正受到越来越多的关注。为了在社会中部署此类系统，代理必须能够在现实世界中的计算和通信约束下建立合作与协调。我们提出了FLCOA框架（五层自主代理间合作/协调的概念化），以阐述自主代理群体中合作与协调如何出现，并强调较低层因素——尤其是计算和通信资源——的影响已被很大程度上忽视。为了研究通信延迟的影响，我们引入了一个带有通信延迟的连续囚徒困境，并用基于LLM的代理进行模拟。随着延迟增加，代理开始利用较慢的响应，即使没有明确指令。有趣的是，过度延迟会减少剥削的循环次数，导致延迟大小与相互合作之间呈现U形关系。这些结果表明，促进合作不仅需要关注高层制度设计，还需要关注较低层因素，如通信延迟和资源分配，指出了多智能体系统研究的新方向。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
