Answers are grounded in this paper and cite their sources.
The Sixth Generation Mobile Communication Technology (6G) is envisioned as a transformative network architecture featuring ultra-high speed, low latency, massive connectivity, and pervasive intelligence to meet the demands of future communication scenarios. To achieve these goals, 6G networks are expected to integrate highly dynamic, heterogeneous, and multi-layered structures. However, this inherent complexity poses significant challenges to traditional rule-based or static network management strategies. In this context, Artificial Intelligence (AI) serves as a foundational technology to enable intelligent, adaptive, and scalable 6G networks. Unfortunately, there is a lack of a panoramic review on AI for the construction of 6G networks. To bridge this gap, this paper presents a thorough survey on AI-driven innovations in 6G networks. We begin with an introduction to 6G networks and the AI techniques commonly employed in 6G networks. Additionally, we propose a set of criteria for evaluating existing AI-driven solutions in 6G networks. We then categorize existing works and conduct a detailed review and analysis on each of them based on our evaluation criteria. Finally, we identify open issues and propose potential directions for future research and development.
No takes yet. Share an insight, caveat, or question.
Shao et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: