Cooperation Breakdown in LLM Agents Under Communication Delays
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918333662625792 |
|---|---|
| author | Nishimoto, Keita Asatani, Kimitaka Sakata, Ichiro |
| author_facet | Nishimoto, Keita Asatani, Kimitaka Sakata, Ichiro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11754 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cooperation Breakdown in LLM Agents Under Communication Delays Nishimoto, Keita Asatani, Kimitaka Sakata, Ichiro Multiagent Systems Artificial Intelligence Computer Science and Game Theory 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. |
| title | Cooperation Breakdown in LLM Agents Under Communication Delays |
| topic | Multiagent Systems Artificial Intelligence Computer Science and Game Theory |
| url | https://arxiv.org/abs/2602.11754 |