用大模型模拟群体智能，发现计算成本高出300倍。
LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?
- 用大模型代替传统算法实现群体行为模拟
- 大模型版本耗时比传统方法高300倍
- 适合研究群体智能原理，不适合实时应用
群体智能描述了简单、去中心化的智能体如何协同产生复杂行为。近年来，该概念被扩展至大语言模型（LLM）驱动的系统，如OpenAI的Swarm（OAS）框架，其中智能体通过自然语言提示进行协调。本文评估此类系统是否真正体现了经典群体智能的核心原则：去中心化、简单性、涌现性和可扩展性。我们基于OAS实现了经典与基于LLM的两种成熟群体算法：Boids和蚁群优化（Ant Colony Optimization）。结果表明，尽管LLM驱动的群体能模拟类群体动态，但存在显著的计算开销。例如，我们的LLM版Boids仿真比传统版本多消耗约300倍的计算时间，凸显当前将大模型驱动的群体应用于实时系统时的局限性。
原文摘要 · Abstract (English)
Swarm intelligence describes how simple, decentralized agents can collectively produce complex behaviors. Recently, the concept of swarming has been extended to large language model (LLM)-powered systems, such as OpenAI's Swarm (OAS) framework, where agents coordinate through natural language prompts. This paper evaluates whether such systems capture the fundamental principles of classical swarm intelligence: decentralization, simplicity, emergence, and scalability. Using OAS, we implement and compare classical and LLM-based versions of two well-established swarm algorithms: Boids and Ant Colony Optimization. Results indicate that while LLM-powered swarms can emulate swarm-like dynamics, they are constrained by substantial computational overhead. For instance, our LLM-based Boids simulation required roughly 300x more computation time than its classical counterpart, highlighting current limitations in applying LLM-driven swarms to real-time systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。