An LLM-based Agentic Framework for Accessible Network Control

2025-09-24

AI Summary

Traditional network management relies heavily on domain-expert operators, imposing significant usability barriers for non-specialist users. To address this, we propose a natural-language-driven, agent-based network management framework. First, we design a device-agnostic intermediate representation (IR) to uniformly model configurations and states across heterogeneous multi-vendor devices. Second, we develop an LLM-powered agent system featuring real-time memory-augmented retrieval, closed-loop external feedback integration, and interactive visualization—enabling conversational configuration, dynamic state awareness, and user intent clarification. To our knowledge, this is the first framework to systematically realize natural-language-controlled management of large-scale heterogeneous networks. We validate its effectiveness on both synthetic datasets and real-world user utterances; a web-based visual interface has been deployed, and feedback from operational scenarios confirms practical viability—thereby advancing the democratization of LLMs in production network management.

Technology Category

• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Traditional approaches to network management have been accessible only to a handful of highly-trained network operators with significant expert knowledge. This creates barriers for lay users to easily manage their networks without resorting to experts. With recent development of powerful large language models (LLMs) for language comprehension, we design a system to make network management accessible to a broader audience of non-experts by allowing users to converse with networks in natural language. To effectively leverage advancements in LLMs, we propose an agentic framework that uses an intermediate representation to streamline configuration across diverse vendor equipment, retrieves the network state from memory in real-time, and provides an interface for external feedback. We also conduct pilot studies to collect real user data of natural language utterances for network control, and present a visualization interface to facilitate dialogue-driven user interaction and enable large-scale data collection for future development. Preliminary experiments validate the effectiveness of our proposed system components with LLM integration on both synthetic and real user utterances. Through our data collection and visualization efforts, we pave the way for more effective use of LLMs and democratize network control for everyday users.

Problem

• Making network management accessible to non-experts via natural language
• Proposing an agentic framework to streamline configuration across diverse equipment
• Collecting real user data and providing a visualization interface for interaction

Innovation

• LLM-based agentic framework for network control
• Intermediate representation for vendor-agnostic configuration
• Real-time network state retrieval with feedback interface