Let Them Talk: A Multi-Level Analysis of Communication Between LLM Agents

A swarm of large language model (LLM) agents has demonstrated remarkable abilities in solving complex tasks by interacting and coordinating with one another at scale. In this work, we investigate how communication affects the behavior of LLMs in repeated multi-agent interactions with incomplete information, such as the Iterated Prisoner's Dilemma and Public Good Game. Our multi-level analysis of agents' signaling behavior, chain of thought, layer activations, and population dynamics reveals that communication generally fosters trust, leading to the emergence of cooperative strategies that benefit both parties in dyadic interaction. However, the same channel also makes the population of agents more exploitable to predatory “free riders" when the benefit of cooperation is non-excludable. Together, these findings underscore crucial ethical and strategic considerations for responsible deployment of multi-agent systems.