Agentic Open RAN: A Deterministic and Auditable Framework for Intent-Driven Radio Control

2026-04-14

AI Summary

This work addresses the challenge in Open RAN of reconciling auditability, deterministic execution, and multi-agent consistency when enabling natural language–driven autonomous control. To this end, the paper proposes A1gent, a novel framework featuring a hierarchical agent architecture that decouples reasoning from execution. In this design, non-real-time rApps leverage large language models to interpret high-level intents and generate typed policies, while near-real-time xApps collaboratively execute deterministic control loops via E2/O1 interfaces. A1gent further introduces policy guards, plane-scoped actions, a fixed-priority conflict resolver, and a training-free KPI memory–driven tuning mechanism. This approach establishes a verifiable mapping from natural language intents to reliable wireless operations, ensuring system auditability while achieving predictable performance adaptation.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Planning, Routing, and Scheduling: Plan Execution and Monitoring

Application Category

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

Abstract

Large language models (LLMs) open new possibilities for agentic control in Open RAN, allowing operators to express intents in natural language while delegating low-level execution to autonomous agents. We present A1gent, an agentic RAN control stack that decouples reasoning from real-time actuation. A non-RT agentic rApp compiles operator goals into typed A1 policy instances, and three task-oriented near-RT agentic xApps enforce them through a deterministic loop with plane-scoped actuation - E2 for mobility and load steering, and O1 for energy orchestration. This agentic reasoning-execution split ensures auditable coordination between RAN intelligent controller (RIC) tiers, supported by encoded guardrails and a fixed-priority action merger for conflict governance. A training-free adaptive policy tuner then refines bounded parameters using KPI memory without retraining, sustaining predictable adaptation. By integrating intent-driven planning with deterministic near-RT execution, A1gent advances Open RAN toward verifiable, self-governing, and reproducible agentic intelligence.

Problem

• Agentic Control
• Open RAN
• Intent-Driven
• Deterministic Execution
• Auditable Coordination

Innovation

• Agentic RAN
• Intent-driven Control
• Deterministic Execution
• Auditable Coordination
• Policy Tuning