Toward E2E Intelligence in 6G Networks: An AI Agent-Based RAN-CN Converged Intelligence Framework

2026-02-27

AI Summary

This work addresses the limitations of conventional 6G network architectures, where dedicated AI models deployed separately in the Radio Access Network (RAN) and Core Network (CN) suffer from poor generalization, fragmented cross-domain decision-making, and high maintenance overhead due to frequent retraining. To overcome these challenges, the paper proposes the first unified RAN-CN intelligent framework leveraging large language models (LLMs) and the ReAct reasoning-action paradigm. By implementing a closed-loop “think-act-observe” mechanism, the framework enables unified, dynamic, and context-aware end-to-end network control without requiring model retraining. Experimental results demonstrate significantly enhanced generalization and adaptability in unseen scenarios, highlighting its potential as a unified intelligent control architecture for 6G networks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent advances in intelligent network control have primarily relied on task-specific Artificial Intelligence (AI) models deployed separately within the Radio Access Network (RAN) and Core Network (CN). While effective for isolated models, these suffer from limited generalization, fragmented decision-making across network domains, and significant maintenance overhead due to frequent retraining. To address these limitations, we propose a novel AI agent-based RAN-CN converged intelligence framework that leverages a Large Language Model (LLM) integrated with the Reasoning and Acting (ReAct) paradigm. The proposed framework enables the AI agent to iteratively reason over real-time, cross-domain state information stored in a centralized monitoring database and to synthesize adaptive control policies through a closed-loop thought-action-observation process. Unlike conventional Machine Learning (ML) based approaches, it does not rely on model retraining. Instead, the AI agent dynamically queries and interprets structured network data to generate context-aware control decisions, allowing for fast and flexible adaptation to changing network conditions. Experimental results demonstrate the enhanced generalization capability and superior adaptability of the proposed framework to previously unseen network scenarios, highlighting its potential as a unified control intelligence for next-generation networks.

Problem

• AI agent
• RAN-CN convergence
• intelligent network control
• generalization
• decision fragmentation

Innovation

• AI Agent
• LLM-based Networking
• RAN-CN Convergence
• ReAct Paradigm
• Zero-Retraining Control