Recent research in Particle Swarm Optimization (PSO)-based Task Scheduling in Cloud Computing emphasizes enhancing scheduling efficiency, scalability, and energy performance through improved and hybrid PSO variants. These approaches optimize task-to-resource mapping by simulating swarm intelligence to minimize makespan, cost, and execution delay while maintaining load balance and QoS requirements. Studies have proposed adaptive and chaotic PSO models, as well as hybrid methods combining PSO with Grey Wolf Optimizer, Genetic Algorithm, and Simulated Annealing to achieve faster convergence and global optimization. The latest advancements highlight PSO’s capability to handle dynamic workloads and heterogeneous environments, making it a powerful meta-heuristic tool for intelligent task scheduling in cloud infrastructures.