Hermes: A Large Language Model Framework on the Journey to Autonomous Networks

Fadhel Ayed1, Ali Maatouk4, Nicola Piovesan1, Antonio De Domenico1, Mohamed Sana1,
Merouane Debbah2, and Zhi-Quan Luo3
1Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France
2Khalifa University of Science and Technology, Abu Dhabi, UAE
3The Chinese University of Hong Kong, Shenzhen, China
4Yale University, New Haven, Connecticut, USA

About Hermes

The drive toward automating cellular network operations has grown with the increasing complexity of these systems. Despite advancements, full network autonomy currently remains out of reach due to reliance on human intervention for modeling network behaviors and defining policies to meet target requirements. Network Digital Twins (NDTs) have shown promise in enhancing network intelligence, but the successful implementation of this technology is constrained by use case-specific architectures, limiting its role in advancing network autonomy. A more capable network intelligence, or "telecommunications brain", is needed to enable seamless, autonomous management of cellular network. Large Language Models (LLMs) have emerged as potential enablers for this vision but face challenges in network modeling, especially in reasoning and handling diverse data types. To address these gaps, we introduce Hermes, a chain of LLM agents that uses structured and explainable logical steps for constructing NDT instances. Hermes allows automatic, reliable, and accurate network modeling of diverse use cases and configurations, thus marking progress toward fully autonomous network operations.

Framework Demonstration

Video demonstration of the Hermes framework in action.

Research Paper

The Hermes framework is presented in detail in our research paper:

"Hermes: A Large Language Model Framework on the Journey to Autonomous Networks"

How to Cite

If you use Hermes in your research, please cite our paper:

@article{hermes2024,
  title = {Hermes: A Large Language Model Framework on the Journey to Autonomous Networks},
  author = {Ayed, Fadhel and Maatouk, Ali and Piovesan, Nicola and De Domenico, Antonio and Sana, Mohamed and Debbah, Merouane and Luo, Zhi-Quan},
  journal = {arXiv preprint},
  year = {2024},
  url = {https://arxiv.org/abs/2411.06490v1}
}