The disaggregation of the Radio Access Network (RAN) introduces architectural flexibility but significant operational complexity, necessitating automated management frameworks. For instance, 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 article, we propose ORION, an intent orchestration framework that integrates Large Language Models (LLMs) through the Model Context Protocol (MCP). It translates natural language slice requests into network policies aligned with O-RAN interfaces, supporting the AI-RAN agentic orchestration and AI-for-RAN paradigms. ORION combines an MCP-based Service Management and Orchestration (SMO) layer with a Non-Real-Time RIC rApp and a Near-Real-Time RIC xApp to enforce Physical Resource Block (PRB) quotas over E2. We evaluate eight LLM configurations across proprietary and open-weight models on a 100-intent workload. Claude Opus 4.5 and GPT-5 achieve 100% policy-creation success with 99% and 96% slice-type classification accuracy, while GPT-5 Nano achieves 97% policy-creation success. The evaluation also assesses MCP tool-use quality, cost-performance trade-offs, resource consumption, and end-to-end control-path latency.

翻译：暂无翻译