Position Paper: Rethinking AI/ML for Air Interface in Wireless Networks

2025-06-13

AI Summary

AI/ML integration into wireless physical and MAC layers remains in its infancy, with 3GPP lacking a systematic, AI-native air interface (AI-Native AI) framework. Method: This paper systematically analyzes key use cases, architectural paradigms, and technical requirements for AI-Native AI from 3GPP SA2 and SA5 studies, integrating communication theory, online learning, lightweight inference, and network function virtualization to propose a 6G-oriented AI-Native air interface research framework. Contribution/Results: It formally defines the standardization roadmap for air interface AI; identifies six critical open research directions; and establishes an industry–academia–research collaboration roadmap. The framework has been preliminarily adopted in 3GPP TR 21.917 and related technical reports, providing both theoretical foundations and practical guidance for deep convergence of communications and AI.

Technology Category

• Planning, Routing, and Scheduling: Plan Execution and Monitoring
• Machine Learning: Efficient ML / Green AI
• Humans and AI: Interaction Techniques and Devices

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

AI/ML research has predominantly been driven by domains such as computer vision, natural language processing, and video analysis. In contrast, the application of AI/ML to wireless networks, particularly at the air interface, remains in its early stages. Although there are emerging efforts to explore this intersection, fully realizing the potential of AI/ML in wireless communications requires a deep interdisciplinary understanding of both fields. We provide an overview of AI/ML-related discussions in 3GPP standardization, highlighting key use cases, architectural considerations, and technical requirements. We outline open research challenges and opportunities where academic and industrial communities can contribute to shaping the future of AI-enabled wireless systems.

Problem

• Exploring AI/ML applications in wireless air interfaces
• Bridging interdisciplinary gaps for AI/ML in wireless networks
• Identifying research challenges for AI-enabled wireless systems

Innovation

• AI/ML application in wireless air interface
• Interdisciplinary AI/ML and wireless integration
• 3GPP standardization for AI/ML in wireless