MX-AI: Agentic Observability and Control Platform for Open and AI-RAN
This work addresses the problem of autonomous management and configuration of future 6G networks for telecom operators and researchers, representing a novel application rather than an incremental improvement.
The paper tackles the challenge of enabling AI-native 6G radio access networks by introducing MX-AI, an end-to-end agentic system that instruments a live 5G Open RAN testbed with LLM-powered agents for observability and control via natural language, achieving a mean answer quality of 4.1/5.0 and 100% decision-action accuracy with 8.8 seconds latency.
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