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.

翻译：无线接入网（RAN）的解耦带来了前所未有的灵活性，但也引入了显著的操作复杂性，从而需要自动化管理框架。然而，当前的开放无线接入网（O-RAN）编排依赖于零散的手动策略，缺乏从高层需求到底层配置的端到端意图保障。本文提出ORION，这是一个符合O-RAN标准的意图编排框架，它通过模型上下文协议（MCP）集成大型语言模型（LLM），将自然语言意图转化为可执行的网络策略。ORION采用分层智能体架构，将基于MCP的、用于语义翻译的服务管理与编排（SMO）层，与用于闭环执行的、部署于非实时无线智能控制器（Non-RT RIC）的rApp和近实时无线智能控制器（Near-RT RIC）的xApp相结合。使用GPT-5、Gemini 3 Pro和Claude Opus进行的广泛评估表明，对于高容量模型，策略生成成功率达到100%，同时突显了推理效率方面的重要权衡。我们证明，ORION通过自动化从意图摄取到E2级执行的完整意图生命周期，降低了配置复杂性，为自主6G网络铺平了道路。