We investigate whether \emph{LLM-based agents} can develop task-oriented communication protocols that differ from standard natural language in collaborative reasoning tasks. Our focus is on two core properties such task-oriented protocols may exhibit: Efficiency -- conveying task-relevant information more concisely than natural language, and Covertness -- becoming difficult for external observers to interpret, raising concerns about transparency and control. To investigate these aspects, we use a referential-game framework in which vision-language model (VLM) agents communicate, providing a controlled, measurable setting for evaluating language variants. Experiments show that VLMs can develop effective, task-adapted communication patterns. At the same time, they can develop covert protocols that are difficult for humans and external agents to interpret. We also observe spontaneous coordination between similar models without explicitly shared protocols. These findings highlight both the potential and the risks of task-oriented communication, and position referential games as a valuable testbed for future work in this area.

翻译：本研究旨在探究基于大语言模型（LLM）的智能体在协作推理任务中，能否发展出有别于标准自然语言的任务导向通信协议。我们重点关注此类协议可能展现的两个核心特性：**效率性**——比自然语言更简洁地传递任务相关信息；以及**隐蔽性**——对外部观察者而言难以解读，从而引发关于透明度与可控性的担忧。为探究这些方面，我们采用指称游戏框架，让视觉语言模型（VLM）智能体在其中进行通信，从而为评估语言变体提供了一个可控、可测量的实验环境。实验表明，VLM能够发展出高效且适应任务的通信模式。同时，它们也能形成对人类及外部智能体难以解读的隐蔽协议。我们还观察到，相似模型之间无需显式共享协议即可实现自发的协调。这些发现既揭示了任务导向通信的潜力，也凸显了其风险，并将指称游戏定位为该领域未来研究的重要测试平台。