Device-to-Device (D2D) communication has emerged as a pivotal technology for fifth-generation (5G) and sixth-generation (6G) wireless networks, enabling direct communication between proximate devices while bypassing the base station. This paradigm promises significant improvements in spectral efficiency, energy efficiency, system capacity, and ultra-low latency communications essential for emerging applications including Vehicle-to-Everything (V2X), Industrial IoT, and extended reality. However, realizing the full potential of D2D communication requires addressing numerous technical challenges including device discovery, mode selection, interference management, power control, security, radio resource allocation, cell densification and offloading, quality of service provisioning, millimeter-wave integration, and seamless handover. The complexity and dynamic nature of these challenges have catalyzed extensive research into Artificial Intelligence (AI) and Machine Learning (ML) solutions. This comprehensive survey presents an exhaustive analysis of AI/ML approaches for D2D communication, spanning from classical techniques such as Fuzzy Logic, Q-Learning, Neural Networks, Evolutionary Algorithms, Genetic Algorithms, Particle Swarm Optimization, and Ant Colony Optimization, to advanced paradigms including Deep Reinforcement Learning (DRL), Graph Neural Networks (GNNs), Federated Learning (FL), Multi-Agent Reinforcement Learning (MARL), Large Language Models (LLMs), Generative AI, Semantic Communication, and Reconfigurable Intelligent Surfaces (RIS). A particular focus is given to the Distributed Artificial Intelligence (DAI) framework utilizing Belief-Desire-Intention eXtended (BDIx) agents, which represents one promising approach toward autonomous, distributed D2D control without base station dependency. We provide detailed taxonomies based on spectrum utilization, control mechanisms, and transmission modes. Comparative analysis through comprehensive tables evaluates performance metrics across over 170 references, including works from 2023-2025 addressing 6G requirements such as sub-terahertz communications, digital twins, and zero-touch network management. Performance ranges presented are indicative values synthesized across heterogeneous simulation setups; different papers employ varying channel models, network densities, and baseline comparisons, and direct cross-study comparison requires normalization to common experimental conditions. The survey identifies twelve critical open issues including scalability, real-world validation, convergence guarantees, AI security, energy efficiency, and standardization challenges. A strategic roadmap for future research directions toward intelligent, autonomous D2D systems in 6G networks is presented. This work serves as a comprehensive reference for researchers and practitioners seeking to leverage AI/ML for next-generation D2D communication systems.
Ioannou et al. (Sat,) studied this question.