Research on Artificial Intelligence (AI)-based Decision Making in Edge Computing focuses on leveraging AI techniques to enable autonomous, real-time, and intelligent decision-making at the network edge, thereby reducing latency, enhancing efficiency, and improving service quality. This area addresses challenges such as limited computational resources, heterogeneous devices, dynamic workloads, and distributed data sources in edge environments. Key research directions include AI-driven resource allocation, task scheduling, and load balancing, as well as predictive analytics for proactive system management. Other emerging topics involve reinforcement learning and deep learning for adaptive edge decisions, context- and workload-aware decision frameworks, and edge–cloud collaborative intelligence for optimized performance. Additionally, research on AI-assisted security and privacy decision-making, energy- and latency-aware optimization, and multi-objective decision models represents significant avenues for advancing autonomous, efficient, and intelligent edge computing systems.