用大模型驱动智能体，模拟蚁群觅食与鸟群迁徙的自组织行为。
Multi-Agent Systems Powered by Large Language Models: Applications in Swarm Intelligence
- 用大模型替代硬编码程序，通过提示词让智能体自主响应环境变化。
- 在蚁群与鸟群模拟中成功实现自组织与涌现行为，验证了方法可行性。
- 适合对群体智能、智能体仿真感兴趣的科研人员与开发者。
本文研究将大语言模型（LLMs）融入多智能体模拟，以提示词替代智能体的硬编码程序。通过构建集成NetLogo仿真平台与OpenAI API的工具链，利用Python扩展实现与GPT-4o通信，支持基于提示词的行为生成。在蚁群觅食与鸟群迁徙两个群体智能系统案例中，采用结构化规则提示与自主知识驱动提示两种方式。结果表明，该方法可有效激发多智能体环境中的自组织过程与涌现行为，为探索自然启发的智能系统提供了新范式。代码与仿真文件已开源：https://github.com/crjimene/swarm_gpt。
原文摘要 · Abstract (English)
This work examines the integration of large language models (LLMs) into multi-agent simulations by replacing the hard-coded programs of agents with LLM-driven prompts. The proposed approach is showcased in the context of two examples of complex systems from the field of swarm intelligence: ant colony foraging and bird flocking. Central to this study is a toolchain that integrates LLMs with the NetLogo simulation platform, leveraging its Python extension to enable communication with GPT-4o via the OpenAI API. This toolchain facilitates prompt-driven behavior generation, allowing agents to respond adaptively to environmental data. For both example applications mentioned above, we employ both structured, rule-based prompts and autonomous, knowledge-driven prompts. Our work demonstrates how this toolchain enables LLMs to study self-organizing processes and induce emergent behaviors within multi-agent environments, paving the way for new approaches to exploring intelligent systems and modeling swarm intelligence inspired by natural phenomena. We provide the code, including simulation files and data at https://github.com/crjimene/swarm_gpt.
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。