Data to 14 Oct 2026

MX-AI: Agentic Observability and Control Platform for Open and AI-RAN

arXiv 2508.09197 ↗First posted 8 Aug 2025cs.NI cs.AIcited by 4

On the map: LLM agents and tool use → Agentic AI for wireless networks

Abstract (arXiv)

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

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use. Builds on 13 of its 23 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

13 of 23 references.

Closest ancestors · 1

Same direction, newest first

2025Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven Networks23 Jul

Other references · 12

2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
2024A Survey on LLM-as-a-Judgecited by 1,423
2023GPTScore: Evaluate as You Desirecited by 361
2024A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directionscited by 25
2024Large Language Models for Networking: Workflow, Advances and Challengescited by 15
2025dApps: Enabling Real-Time AI-Based Open RAN Controlcited by 14
2020Dynamic RAN Slicing for Service-Oriented Vehicular Networks via Constrained Learningcited by 13
2025Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiencescited by 12
2024LINKs: Large Language Model Integrated Management for 6G Empowered Digital Twin NetworKscited by 7
2025Hierarchical Debate-Based Large Language Model (LLM) for Complex Task Planning of 6G Network Managementcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

2026Agentic AI for Intent-driven Optimization in Cell-free O-RANcited by 2
2026Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Modelscited by 1
2026AGORA: Agentic Green Orchestration Architecture for Beyond 5G Networkscited by 0
2026From RAN Control to Agentic Intelligence: Architecture and Vision for Energy Efficient AI-RANcited by 0

Similar, not cited

Close in wording, no citation either way