Large Language Models for computer networking operations and management: A survey on applications, key techniques, and opportunities

This survey examines the application of Large Language Models (LLMs) in network operations and management (NO&M). It outlines the transformation in NO&M driven by LLMs, highlighting their potential to address challenges across network design, automation, optimization, and security domains. The paper explores how LLMs enhance traditional methods by automating complex tasks, improving network agility, and providing solutions to emerging network demands. We present our methodology for a systematic literature review and analyze how LLMs complement network technologies, including Software-Defined Networking, Network Function Virtualization, Intent-Based Networking, and Zero-Touch Network. The survey categorizes existing research into key application areas, providing comparisons between LLM-based approaches and traditional methods. We identify current limitations, such as integration with legacy systems, explainability, data privacy, and computational scalability. Additionally, we propose future research directions, including domain-specific efficient architectures, advanced intent-based management, privacy-preserving techniques, integration with next-generation networks, sustainable LLM solutions, cross-domain collaboration frameworks, and ethical considerations. Our findings offer insights for researchers and practitioners aiming to leverage LLMs for intelligent network management in complex and dynamic environments.