LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit communication, less is known about how interacting agents coordinate implicitly. In particular, agents may engage in covert communication, relying on indirect or non-linguistic signals embedded in their actions rather than on explicit messages. This paper presents a game-theoretic study of covert communication in LLM-driven multi-agent systems. We analyse interactions across four canonical game-theoretic settings under different communication regimes, including explicit, restricted, and absent communication. Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.

翻译：基于大语言模型（LLM）的智能体日益在多智能体环境中运行，这些环境需要策略性交互与协调。现有研究主要集中于单个智能体或共享显式通信的交互智能体，而对于交互智能体如何实现隐式协调则知之甚少。具体而言，智能体可能进行隐蔽通信，依赖其行为中嵌入的间接或非语言信号，而非显式消息。本文对LLM驱动的多智能体系统中的隐蔽通信进行了博弈论研究。我们在不同通信机制（包括显式通信、受限通信和无通信）下，分析了四种经典博弈论设定中的交互。考虑到智能体的异质性人格以及单次与重复博弈，我们刻画了隐蔽信号何时出现，以及它们如何影响协调与策略结果。