AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks

2025-08-25

AI Summary

Current Open RAN deployments rely heavily on static configuration and manual intervention, hindering autonomous optimization. To address this, we propose AgentRAN—a 6G-oriented, AI-native agent architecture that enables distributed, intent-driven intelligent coordination via natural language instructions, supporting self-organizing management across spatiotemporal scales and protocol layers. Our key contributions are: (1) a scalable, hierarchical self-organizing multi-agent structure; (2) an AI-RAN Factory that automatically synthesizes domain-specific agents on demand, enabling continuous evolution of network control policies; and (3) tight integration of large language models with structured dialog-based negotiation for robust intent parsing, collaborative decision-making, and closed-loop control. Evaluated on a 5G testbed, AgentRAN dynamically balances heterogeneous user demands, achieves efficient cross-layer resource coordination through cascaded intent execution, and significantly enhances network autonomy and environmental adaptability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The Open RAN movement has catalyzed a transformation toward programmable, interoperable cellular infrastructures. Yet, today's deployments still rely heavily on static control and manual operations. To move beyond this limitation, we introduce AgenRAN, an AI-native, Open RAN-aligned agentic framework that generates and orchestrates a fabric of distributed AI agents based on Natural Language (NL) intents. Unlike traditional approaches that require explicit programming, AgentRAN's LLM-powered agents interpret natural language intents, negotiate strategies through structured conversations, and orchestrate control loops across the network. AgentRAN instantiates a self-organizing hierarchy of agents that decompose complex intents across time scales (from sub-millisecond to minutes), spatial domains (cell to network-wide), and protocol layers (PHY/MAC to RRC). A central innovation is the AI-RAN Factory, an automated synthesis pipeline that observes agent interactions and continuously generates new agents embedding improved control algorithms, effectively transforming the network from a static collection of functions into an adaptive system capable of evolving its own intelligence. We demonstrate AgentRAN through live experiments on 5G testbeds where competing user demands are dynamically balanced through cascading intents. By replacing rigid APIs with NL coordination, AgentRAN fundamentally redefines how future 6G networks autonomously interpret, adapt, and optimize their behavior to meet operator goals.

Problem

• Autonomous control of open 6G networks through AI agents
• Replacing static network control with natural language intents
• Dynamic orchestration of distributed AI agents across protocol layers

Innovation

• LLM-powered agents interpret natural language intents
• Self-organizing hierarchy decomposes complex intents
• AI-RAN Factory continuously generates improved control agents