• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

由大语言模型驱动的多智能体系统：群体智能中的应用。

Multi-agent systems powered by large language models: applications in swarm intelligence.

作者信息

Jimenez-Romero Cristian, Yegenoglu Alper, Blum Christian

机构信息

ETIS Laboratory, ENSEA, CNRS, UMR8051, CY Cergy-Paris University, Cergy, France.

Independent Researcher, Jülich, Germany.

出版信息

Front Artif Intell. 2025 May 21;8:1593017. doi: 10.3389/frai.2025.1593017. eCollection 2025.

DOI:10.3389/frai.2025.1593017
PMID:40469074
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12135685/
Abstract

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.

摘要

这项工作通过用大语言模型驱动的提示替换智能体的硬编码程序，研究了将大语言模型集成到多智能体模拟中。所提出的方法在群体智能领域的两个复杂系统示例的背景下进行了展示：蚁群觅食和鸟群聚集。本研究的核心是一个将大语言模型与NetLogo模拟平台集成的工具链，利用其Python扩展通过OpenAI API与GPT-4o进行通信。这个工具链有助于生成提示驱动的行为，使智能体能够对环境数据做出自适应响应。对于上述两个示例应用，我们既使用了结构化的、基于规则的提示，也使用了自主的、知识驱动的提示。我们的工作展示了这个工具链如何使大语言模型能够研究自组织过程并在多智能体环境中诱导涌现行为，为探索智能系统和模拟受自然现象启发的群体智能的新方法铺平了道路。我们在https://github.com/crjimene/swarm_gpt上提供了代码，包括模拟文件和数据。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/17636be87cbf/frai-08-1593017-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/ace91afc989f/frai-08-1593017-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/ea0eb515c996/frai-08-1593017-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/9cc04de55812/frai-08-1593017-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/da2308e59423/frai-08-1593017-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/3bfabe25f25b/frai-08-1593017-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/2f0a9cfea8e2/frai-08-1593017-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/eac78fa1e439/frai-08-1593017-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/c3b89b2ade10/frai-08-1593017-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/da71e2db7660/frai-08-1593017-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/9549ddfeb69d/frai-08-1593017-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/dd2ad79b0440/frai-08-1593017-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/17636be87cbf/frai-08-1593017-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/ace91afc989f/frai-08-1593017-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/ea0eb515c996/frai-08-1593017-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/9cc04de55812/frai-08-1593017-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/da2308e59423/frai-08-1593017-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/3bfabe25f25b/frai-08-1593017-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/2f0a9cfea8e2/frai-08-1593017-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/eac78fa1e439/frai-08-1593017-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/c3b89b2ade10/frai-08-1593017-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/da71e2db7660/frai-08-1593017-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/9549ddfeb69d/frai-08-1593017-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/dd2ad79b0440/frai-08-1593017-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b838/12135685/17636be87cbf/frai-08-1593017-g0012.jpg

相似文献

1
Multi-agent systems powered by large language models: applications in swarm intelligence.由大语言模型驱动的多智能体系统：群体智能中的应用。
Front Artif Intell. 2025 May 21;8:1593017. doi: 10.3389/frai.2025.1593017. eCollection 2025.
2
Intelligent Fish-Inspired Foraging of Swarm Robots with Sub-Group Behaviors Based on Neurodynamic Models.基于神经动力学模型的具有子群行为的群体机器人智能鱼启发式觅食
Biomimetics (Basel). 2024 Jan 1;9(1):16. doi: 10.3390/biomimetics9010016.
3
Learning to Make Rare and Complex Diagnoses With Generative AI Assistance: Qualitative Study of Popular Large Language Models.利用生成式人工智能辅助学习罕见且复杂的诊断：对流行的大型语言模型的定性研究。
JMIR Med Educ. 2024 Feb 13;10:e51391. doi: 10.2196/51391.
4
An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing: Algorithm Development and Validation Study.零样本临床自然语言处理中大型语言模型提示策略的实证评估：算法开发与验证研究
JMIR Med Inform. 2024 Apr 8;12:e55318. doi: 10.2196/55318.
5
Privacy-ensuring Open-weights Large Language Models Are Competitive with Closed-weights GPT-4o in Extracting Chest Radiography Findings from Free-Text Reports.在从自由文本报告中提取胸部X光检查结果方面，确保隐私的开放权重大型语言模型与封闭权重的GPT-4o具有竞争力。
Radiology. 2025 Jan;314(1):e240895. doi: 10.1148/radiol.240895.
6
Emotional prompting amplifies disinformation generation in AI large language models.情感提示会放大人工智能大语言模型中的虚假信息生成。
Front Artif Intell. 2025 Apr 7;8:1543603. doi: 10.3389/frai.2025.1543603. eCollection 2025.
7
Biomedical knowledge graph-optimized prompt generation for large language models.生物医学知识图谱优化的大语言模型提示生成。
Bioinformatics. 2024 Sep 2;40(9). doi: 10.1093/bioinformatics/btae560.
8
Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review.用于肿瘤学健康信息提取的大语言模型应用：范围综述
JMIR Cancer. 2025 Mar 28;11:e65984. doi: 10.2196/65984.
9
AI in Home Care-Evaluation of Large Language Models for Future Training of Informal Caregivers: Observational Comparative Case Study.家庭护理中的人工智能——对用于未来非正式护理人员培训的大语言模型的评估：观察性比较案例研究
J Med Internet Res. 2025 Apr 28;27:e70703. doi: 10.2196/70703.
10
Accuracy of a Commercial Large Language Model (ChatGPT) to Perform Disaster Triage of Simulated Patients Using the Simple Triage and Rapid Treatment (START) Protocol: Gage Repeatability and Reproducibility Study.商用大型语言模型（ChatGPT）运用简单分诊与快速治疗（START）协议对模拟患者进行灾难分诊的准确性：再现性和可重复性研究。
J Med Internet Res. 2024 Sep 30;26:e55648. doi: 10.2196/55648.

本文引用的文献

1
SNN4Agents: a framework for developing energy-efficient embodied spiking neural networks for autonomous agents.SNN4Agents：用于为自主智能体开发节能型具身脉冲神经网络的框架。
Front Robot AI. 2024 Jul 26;11:1401677. doi: 10.3389/frobt.2024.1401677. eCollection 2024.
2
Agent-based modeling in ecological economics.基于主体的建模在生态经济学中的应用。
Ann N Y Acad Sci. 2010 Jan;1185:39-53. doi: 10.1111/j.1749-6632.2009.05286.x.