IntAgent: NWDAF-Based Intent LLM Agent Towards Advanced Next Generation Networks

2026-01-19

AI Summary

This work proposes IntAgent, an intelligent intent-driven agent that integrates the Network Data Analytics Function (NWDAF) with large language models (LLMs) to enable high-level intent-based network automation. Its key innovation lies in the first-time embedding of an intent-aware tool engine directly within the NWDAF analytics framework, which—combined with standardized 3GPP data sources and an MCP tool server—enables context-aware dynamic reasoning and on-demand tool invocation. The efficacy of IntAgent is demonstrated through two representative use cases: ML-driven traffic forecasting and scheduled policy enforcement. Experimental results show that IntAgent can autonomously and accurately execute complex network operations, significantly enhancing the self-governing capabilities and automation level of operator networks.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Intent-based networks (IBNs) are gaining prominence as an innovative technology that automates network operations through high-level request statements, defining what the network should achieve. In this work, we introduce IntAgent, an intelligent intent LLM agent that integrates NWDAF analytics and tools to fulfill the network operator's intents. Unlike previous approaches, we develop an intent tools engine directly within the NWDAF analytics engine, allowing our agent to utilize live network analytics to inform its reasoning and tool selection. We offer an enriched, 3GPP-compliant data source that enhances the dynamic, context-aware fulfillment of network operator goals, along with an MCP tools server for scheduling, monitoring, and analytics tools. We demonstrate the efficacy of our framework through two practical use cases: ML-based traffic prediction and scheduled policy enforcement, which validate IntAgent's ability to autonomously fulfill complex network intents.

Problem

• Intent-based Networking
• Next Generation Networks
• Network Automation
• NWDAF
• LLM Agent

Innovation

• Intent-based Networking
• NWDAF
• LLM Agent
• 3GPP-compliant analytics
• Autonomous Network Management