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

TL;DR

This paper introduces A1gent, a framework for intent-driven, deterministic, and auditable control in Open RAN using agentic reasoning and real-time execution, enhancing verifiability and adaptability.

Contribution

It presents a novel agentic RAN control stack that separates reasoning from actuation, enabling auditable, deterministic, and adaptive radio management.

Findings

Decouples reasoning from real-time actuation for auditable control.

Uses a training-free policy tuner for adaptive parameter refinement.

Integrates intent-driven planning with deterministic execution for verifiable RAN management.

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.