EUVIMEDEUVIMED entdecken
Crossref

AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems Using Hybrid Large Language Models

Tingting Yang, Ping Feng, Qixin Guo, Jindi Zhang, Xiufeng Zhang, Jiahong Ning, Xinghan Wang, Zhongyang Mao

IEEE Transactions on Cognitive Communications and Networking · 2025-04 · 11 (2) · 987-998

DOI: 10.1109/tccn.2025.3528892 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2025-04. Verfasst von Tingting Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Heterogeneous multi-agent systems (HMAS) comprise various intelligent agents with specialized functions, such as drones, ground robots, and automated devices, working in coordinated settings. This paper presents AutoHMA-LLM, a novel framework that combines Large Language Models (LLMs) with classical control algorithms to address the challenges of task coordination and scheduling in complex, dynamic environments. The framework is designed with a multi-tier architecture, utilizing a cloud-based LLM as the central planner alongside device-specific LLMs and Generative Agents to improve task execution efficiency and accuracy. Specifically targeting dynamic scenarios, the system enhances resource utilization and stabilizes task execution through refined task scheduling and real-time feedback mechanisms. In experiments conducted across logistics, inspection, and search & rescue scenarios, AutoHMA-LLM demonstrated a 5.7% improvement in task completion accuracy, a 46% reduction in communication steps, and a 31% decrease in token usage and API calls compared to baseline methods. These results highlight our framework’s scalability and efficiency, offering substantial support for effective multi-agent collaboration in complex, resource-constrained environments.

Zitieren

APA

Yang, T., Feng, P., Guo, Q., Zhang, J., Zhang, X., Ning, J., Wang, X., & Mao, Z. (2025). AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems Using Hybrid Large Language Models. IEEE Transactions on Cognitive Communications and Networking, 11(2), 987-998. https://doi.org/10.1109/tccn.2025.3528892

Vancouver

Yang T, Feng P, Guo Q, Zhang J, Zhang X, Ning J, et al. AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems Using Hybrid Large Language Models. IEEE Transactions on Cognitive Communications and Networking. 2025;11(2):987-998. doi:10.1109/tccn.2025.3528892

BibTeX
@article{Yang2025,
  author = {Yang, Tingting and Feng, Ping and Guo, Qixin and Zhang, Jindi and Zhang, Xiufeng and Ning, Jiahong and Wang, Xinghan and Mao, Zhongyang},
  title = {AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems Using Hybrid Large Language Models},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2025},
  volume = {11},
  number = {2},
  pages = {987--998},
  doi = {10.1109/tccn.2025.3528892}
}
Kostenlos starten →