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

TL;DR

Her Hermes, a chain of LLM agents that uses structured and explainable logical steps for constructing NDT instances through structured and explainable logical steps, allows automatic, reliable, and accurate network modeling of diverse use cases and configurations, thus marking progress toward fully autonomous network operations.

Abstract

The drive toward automating cellular network operations has grown with the increasing complexity of these systems. Despite advancements, full 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 "blueprints" for constructing NDT instances through structured and explainable logical steps. Hermes allows automatic, reliable, and accurate network modeling of diverse use cases and configurations, thus marking progress toward fully autonomous network operations.

Figures (4)

• Figure 1: Policy deployment in autonomous networks.
• Figure 2: Architecture of the Hermes Framework.
• Figure 3: Example of a blueprint designed by Hermes for the power control task.
• Figure 4: Success rate achieved by different solutions at different problem complexity.