ORION: Intent-Aware Orchestration in Open RAN for SLA-Driven Network Management

TL;DR

ORION is an intent-aware orchestration framework for Open RAN that uses LLMs to translate high-level requirements into network policies, enabling automated, end-to-end network management for future 6G networks.

Contribution

It introduces a hierarchical architecture integrating LLMs via MCP for semantic translation and closed-loop enforcement, advancing automated network management in Open RAN.

Findings

100% policy generation success with high-capacity models

Significant reduction in provisioning complexity

Demonstrated trade-offs in reasoning efficiency

Abstract

The disaggregation of the Radio Access Network (RAN) introduces unprecedented flexibility but significant operational complexity, necessitating automated management frameworks. However, current Open RAN (O-RAN) orchestration relies on fragmented manual policies, lacking end-to-end intent assurance from high-level requirements to low-level configurations. In this paper, we propose ORION, an O-RAN compliant intent orchestration framework that integrates Large Language Models (LLMs) via the Model Context Protocol (MCP) to translate natural language intents into enforceable network policies. ORION leverages a hierarchical agent architecture, combining an MCP-based Service Management and Orchestration (SMO) layer for semantic translation with a Non-Real-Time RIC rApp and Near-Real-Time RIC xApp for closed-loop enforcement. Extensive evaluations using GPT-5, Gemini 3 Pro, and Claude Opus demonstrate a 100% policy generation success rate for high-capacity models, highlighting significant trade-offs in reasoning efficiency. We show that ORION reduces provisioning complexity by automating the complete intent lifecycle, from ingestion to E2-level enforcement, paving the way for autonomous 6G networks.