用大模型打造可自然语言操控的6G无线网络系统
MX-AI: Agentic Observability and Control Platform for Open and AI-RAN
- 在5G开放基站上部署大模型驱动的智能体网络，实现云端协同
- 自然语言指令下平均回答质量4.1/5，决策动作准确率100%，端到端延迟仅8.8秒
- 开源全部组件，适合研究智能无线网络和自主系统的人群
未来6G无线接入网（RAN）将实现人工智能原生化：由自治智能体在云-边协同中感知、推理并重构网络。本文提出MX-AI，首个端到端智能体系统，具备三大能力：(i) 基于OpenAirInterface（OAI）与FlexRIC的实时5G开放RAN测试床，(ii) 在服务管理与编排（SMO）层部署图结构的大语言模型（LLM）智能体，(iii) 支持通过自然语言意图实现对6G RAN资源的可观测性与控制。在50个真实运维查询中，MX-AI平均回答质量达4.1/5.0，决策-动作准确率为100%，采用GPT-4.1时端到端延迟仅为8.8秒。结果表明其性能媲美人工专家，验证了实际应用可行性。项目已公开智能体图谱、提示词与评测工具包，以推动开放研究。演示视频见：https://www.youtube.com/watch?v=CEIya7988Ug&t=285s&ab_channel=BubbleRAN
原文摘要 · Abstract (English)
Future 6G radio access networks (RANs) will be artificial intelligence (AI)-native: observed, reasoned about, and re-configured by autonomous agents cooperating across the cloud-edge continuum. We introduce MX-AI, the first end-to-end agentic system that (i) instruments a live 5G Open RAN testbed based on OpenAirInterface (OAI) and FlexRIC, (ii) deploys a graph of Large-Language-Model (LLM)-powered agents inside the Service Management and Orchestration (SMO) layer, and (iii) exposes both observability and control functions for 6G RAN resources through natural-language intents. On 50 realistic operational queries, MX-AI attains a mean answer quality of 4.1/5.0 and 100 % decision-action accuracy, while incurring only 8.8 seconds end-to-end latency when backed by GPT-4.1. Thus, it matches human-expert performance, validating its practicality in real settings. We publicly release the agent graph, prompts, and evaluation harness to accelerate open research on AI-native RANs. A live demo is presented here: https://www.youtube.com/watch?v=CEIya7988Ug&t=285s&ab_channel=BubbleRAN
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。