Flocking is a behavior where multiple agents in a system attempt to stay close to each other while avoiding collision and maintaining a desired formation. This is observed in the natural world and has applications in robotics, including natural disaster search and rescue, wild animal tracking, and perimeter surveillance and patrol. Recently, large language models (LLMs) have displayed an impressive ability to solve various collaboration tasks as individual decision-makers. Solving multi-agent flocking with LLMs would demonstrate their usefulness in situations requiring spatial and decentralized decision-making. Yet, when LLM-powered agents are tasked with implementing multi-agent flocking, they fall short of the desired behavior. After extensive testing, we find that agents with LLMs as individual decision-makers typically opt to converge on the average of their initial positions or diverge from each other. After breaking the problem down, we discover that LLMs cannot understand maintaining a shape or keeping a distance in a meaningful way. Solving multi-agent flocking with LLMs would enhance their ability to understand collaborative spatial reasoning and lay a foundation for addressing more complex multi-agent tasks. This paper discusses the challenges LLMs face in multi-agent flocking and suggests areas for future improvement and research.

翻译：集群行为是指系统中多个智能体试图保持彼此接近，同时避免碰撞并维持期望队形的行为。这种现象在自然界中普遍存在，并在机器人学中具有广泛应用，包括自然灾害搜救、野生动物追踪以及周界监视与巡逻。近年来，大语言模型（LLMs）作为独立决策单元在解决各类协作任务中展现出卓越能力。使用LLMs解决多智能体集群问题将证明其在需要空间与分布式决策场景中的实用性。然而，当由LLM驱动的智能体被赋予实现多智能体集群任务时，其行为往往无法达到预期效果。经过大量测试，我们发现以LLMs作为独立决策单元的智能体通常倾向于收敛于初始位置的平均点，或彼此逐渐分散。通过问题分解，我们发现LLMs无法以有意义的方式理解队形保持或距离维持。利用LLMs解决多智能体集群问题将提升其理解协作空间推理的能力，并为处理更复杂的多智能体任务奠定基础。本文探讨了LLMs在多智能体集群任务中面临的挑战，并提出了未来改进与研究的重点方向。