Cellular-X: An LLM-empowered Cellular Agent for Efficient Base Station Operations
Liujianfu Wang, Xinyi Long, Yuyang Du, Xiaoyan Liu, Kexin Chen, Soung Chang Liew
TL;DR
Cellular-X tackles the challenge of scalable, automated maintenance of dense cellular BSs, where manual configuration and extensive document lookup are error-prone. The authors propose a four-subsystem agent that combines a multimodal LLM, retrieval-augmented generation, and iterative self-correction to generate and refine BS configurations (EPC/ENB) from user prompts. The RAG subsystem retrieves information from standards like 3GPP documents using a Top-$k$ selection over cosine similarities, enhancing accuracy for technical queries. The system is demonstrated on a USRP X310 SDR testbed with srsRAN LTE, achieving automated setup, document-based QA, and voice-controlled reporting, indicating practical benefits for field engineers and scalable BS maintenance. The work provides a concrete, real-world demonstration of LLM-enabled autonomous maintenance in cellular networks and suggests a path toward reducing manual scripting and expert time in BS operations.
Abstract
This paper introduces Cellular-X, an LLM-powered agent designed to automate cellular base station (BS) maintenance. Leveraging multimodal LLM and retrieval-augmented generation (RAG) techniques, Cellular-X significantly enhances field engineer efficiency by quickly interpreting user intents, retrieving relevant technical information, and configuring a BS through iterative self-correction. Key features of the demo include automatic customized BS setup, document-based query answering, and voice-controlled configuration reporting and revision. We implemented Cellular-X on a USRP X310 testbed for demonstration. Demo videos and implementation details are available at https://github.com/SeaBreezing/Cellular-X.