2026· IEEE Open Journal of the Communications Society· Vol 7, pp. 12301-12326· 0 citations· 96 references
TL;DR
A detailed review of the evolution of methodologies, from rule-based heuristics to deep reinforcement learning (DRL), federated learning (FL), quantum annealing, and, ultimately, the emerging Agentic AI paradigm is provided.
Abstract
The progression toward 6G mobile networks requires a transition from static network designs to Artificial Intelligence (AI)-native architectures. This survey examines the integration of resource allocation (RA) and network slicing (NS) within the Open Radio Access Network (O-RAN), enabling AI-driven network management. It provides a detailed review of the evolution of methodologies, from rule-based heuristics to deep reinforcement learning (DRL), federated learning (FL), quantum annealing, and, ultimately, the emerging Agentic AI paradigm. Agentic AI leverages autonomous agents and LLMs to achieve Zero-Touch Management (ZTM) through intent-based decision-making. The recently proposed frameworks for AI-Native RAN orchestration are reviewed, the key research gaps in integrating agentic intelligence with O-RAN are identified, and a structured map of the challenges associated with the realization of safe and reliable agentic autonomous 6G networks is presented.
The sixth-generation (6G) mobile communication system is anticipated to provide unprecedented performance, but faces a sustainability barrier from overactivated access points (APs). This study addresses energy-efficient operation in the 6G artificial intelligence–radio access network (AI-RAN) by jointly optimizing AP s...
Seonghoon Kim, Dong-eui Kim, Jih-Wan P. Choi· IEEE Transactions on Wireles...· 0 citations
A comprehensive review of AI-enabled O-RAN systems and a taxonomy of AI approaches for O-RAN, covering machine learning, deep reinforcement learning (DRL), digital-twin-assisted optimization, and emerging foundation-model-based architectures are presented.
Ryan Barker, Alireza Ebrahimi Dorcheh, Tolunay Seyfi et al.· 0 citations
Fifth generation (5G) networks enable radio access network (RAN) slicing, allowing a shared physical infrastructure to be partitioned into multiple logical slices, each tailored to meet heterogeneous service requirements. Slice tenants specify service-level agreements (SLAs) that must be satisfied; however, inefficient...
Femi.A. Elegbeleye· Indonesian Journal of Inform...· 0 citations
This paper places the terrestrial-satellite UAV handover decision inside the near-real-time RIC as an xApp, using a deep reinforcement learning (DRL) framework that combines a Deep Q-Network (DQN) with Prioritized Experience Replay (PER) and a reward shaped to weigh the long-term cost of switching against the reliabili...
Anirudh Warrier, Saba Al-Rubaye· IEEE Access· 0 citations
This paper addresses the challenges of dynamic resource allocation and scheduling in 6G in-X subnetworks supporting applications with heterogeneous characteristics by proposing a novel framework that combines Multi-Agent Reinforcement Learning (MARL), Federated Learning (FL), and Explainable AI (XAI).
Ramoni O. Adeogun· 2026 IEEE 104th Vehicular Te...· 0 citations