Closed-loop Intelligence Using Large Language Models in Wireless Networks

Large Language Models (LLMs) are emerging as a transformative tool for wireless network management, offering the ability to interpret natural language instructions, reason over diverse data types, and adapt rapidly through in-context learning. Their generalization capabilities make them promising candidates for acting as the intelligent core within the Open Radio Access Networks (O-RAN), enabling more robust and flexible control of network behavior. However, it remains unclear how to systematically integrate, evaluate, and compare different LLMs for specific tasks in live network deployments. We present Closed-loop Intelligence using LLMs (CLI-LLM), an open-source framework that transforms real-time network metrics and operator intents into automated network control actions. The goal of this demo is to showcase how different LLMs, whether commercial or open-source, can be integrated into the RAN Intelligent Controller (RIC) to handle tasks such as resource allocation, while also providing time-series analysis capabilities, including anomaly detection and trend prediction.