NextG-GPT: Leveraging GenAI for Advancing Wireless Networks and Communication Research

2025-05-25

AI Summary

To address inefficient knowledge retrieval and poor domain adaptability of large language models (LLMs) in 6G wireless communications research, this paper proposes the first Retrieval-Augmented Generation (RAG)-LLM co-design framework tailored for wireless networks. The framework integrates RAG with state-of-the-art LLMs—including Mistral-7B, Mixtral-8×7B, and LLaMA3.1-8B/70B—and constructs a domain-specific corpus encompassing heterogeneous sources such as O-RAN specifications, 5G/6G standards, ORAN-13K-Bench, and TeleQnA. Its key innovation lies in enabling context-aware, real-time technical question answering—overcoming fundamental limitations of general-purpose LLMs in protocol comprehension and standards document reasoning. Experimental results demonstrate that LLaMA3.1-70B achieves 86.2% answer accuracy and 90.6% relevance on wireless systems QA tasks, significantly outperforming baseline models. This work establishes a new AI-augmented paradigm for telecommunications research and standardization.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent Communication

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Artificial intelligence (AI) and wireless networking advancements have created new opportunities to enhance network efficiency and performance. In this paper, we introduce Next-Generation GPT (NextG-GPT), an innovative framework that integrates retrieval-augmented generation (RAG) and large language models (LLMs) within the wireless systems' domain. By leveraging state-of-the-art LLMs alongside a domain-specific knowledge base, NextG-GPT provides context-aware real-time support for researchers, optimizing wireless network operations. Through a comprehensive evaluation of LLMs, including Mistral-7B, Mixtral-8x7B, LLaMa3.1-8B, and LLaMa3.1-70B, we demonstrate significant improvements in answer relevance, contextual accuracy, and overall correctness. In particular, LLaMa3.1-70B achieves a correctness score of 86.2% and an answer relevancy rating of 90.6%. By incorporating diverse datasets such as ORAN-13K-Bench, TeleQnA, TSpec-LLM, and Spec5G, we improve NextG-GPT's knowledge base, generating precise and contextually aligned responses. This work establishes a new benchmark in AI-driven support for next-generation wireless network research, paving the way for future innovations in intelligent communication systems.

Problem

• Enhancing wireless network efficiency using AI and LLMs
• Providing real-time context-aware support for wireless researchers
• Improving answer relevance and accuracy in wireless communication

Innovation

• Integrates RAG and LLMs for wireless systems
• Uses domain-specific knowledge for real-time support
• Evaluates multiple LLMs for improved accuracy