Generative AI-in-the-loop: Integrating LLMs and GPTs into the Next Generation Networks

TL;DR

This work proposes generative AI-in-the-loop, a framework that fuses large language models (LLMs) with traditional ML to manage next-generation mobile networks. It contrasts LLMs’ semantic understanding and reasoning with the efficiency of conventional ML, and introduces a three-level architecture (ML layer, LLM layer, human oversight) to orchestrate network tasks while mitigating hallucinations. The paper details how LLMs can augment data, design, and lifecycle management across the ML pipeline, and outlines deployment strategies (centralized, distributed, hybrid) to suit privacy and scalability. A case study demonstrates that synthesizing data with GPT-3.5 can significantly improve intrusion-detection performance, underscoring the practical potential of LLM-augmented ML in 6G/RAN contexts, with caveats about data quality and verification. Overall, the work provides a comprehensive refinement of prior surveys, offering concrete pathways for integrating generative AI with ML-driven networks and highlighting supervisory mechanisms to ensure reliability.

Abstract

In recent years, machine learning (ML) techniques have created numerous opportunities for intelligent mobile networks and have accelerated the automation of network operations. However, complex network tasks may involve variables and considerations even beyond the capacity of traditional ML algorithms. On the other hand, large language models (LLMs) have recently emerged, demonstrating near-human-level performance in cognitive tasks across various fields. However, they remain prone to hallucinations and often lack common sense in basic tasks. Therefore, they are regarded as assistive tools for humans. In this work, we propose the concept of "generative AI-in-the-loop" and utilize the semantic understanding, context awareness, and reasoning abilities of LLMs to assist humans in handling complex or unforeseen situations in mobile communication networks. We believe that combining LLMs and ML models allows both to leverage their respective capabilities and achieve better results than either model alone. To support this idea, we begin by analyzing the capabilities of LLMs and compare them with traditional ML algorithms. We then explore potential LLM-based applications in line with the requirements of next-generation networks. We further examine the integration of ML and LLMs, discussing how they can be used together in mobile networks. Unlike existing studies, our research emphasizes the fusion of LLMs with traditional ML-driven next-generation networks and serves as a comprehensive refinement of existing surveys. Finally, we provide a case study to enhance ML-based network intrusion detection with synthesized data generated by LLMs. Our case study further demonstrates the advantages of our proposed idea.

Figures (5)

• Figure 1: Summary of concepts related to the topic of this work, including AI, ML, GAI, NN, LLM, GPT, and AGI.
• Figure 2: An illustration of “generative AI-in-the-loop” in the next-generation network. LLMs act as an intermediary between human-level management and traditional ML and optimization algorithms in several ways: automate network control based on semantic intentions, generate semantic-based explanations, and perform model and network management.
• Figure 3: Different ways to enhance ML models with LLMs. The life cycle of ML models includes four stages: requirement stage, data processing stage, operation stage, and model development stage. LLMs can be integrated into each stage.
• Figure 4: Three ways to combine LLMs with ML models. (a) Both LLMs and ML models are deployed at the center. They are combined for network management. (b) Both LLMs and ML models are deployed in a distributed manner for Multi-Agent interaction. (c) LLMs are deployed at the center for management, and ML models are deployed in a distributed manner for local training and inference.
• Figure 5: Accuracy and F1-score of network intrusion detection using synthetic data.