From Optimization to Autonomy: A Survey on Resource Allocation for Network Slicing in O-RAN

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.