Cloud computing resource management presents a formidable optimization challenge characterized by dynamic and unpredictable workloads, heterogeneous resource pools, competing multi-objective trade-offs among energy consumption, Service Level Agreement (SLA) compliance, resource utilization, makespan, and operational cost, as well as the NP-hard combinatorial nature of core sub-problems including Virtual Machine (VM) placement, task scheduling, and dynamic resource scaling. Existing approaches suffer from well-documented limitations: static heuristics such as First Fit Decreasing (FFD) and Round-Robin (RR) lack adaptability to workload fluctuations; single metaheuristics including Particle Swarm Optimization (PSO) and Genetic Algorithms (GA) exhibit premature convergence and maintain a fixed exploration–exploitation balance; and pure Reinforcement Learning (RL) methods, while adaptive, are sample-inefficient and transfer poorly across workload types. In this paper, we propose World Hyper-Heuristic (WHH) for Cloud Resource Management (World-CRM), an extended adaptation of the WHH originally introduced by Daliri et al. [1] in expert systems with applications. World-CRM adapts the World's novel RL-based dynamic exploration–exploitation switching mechanism to cloud environments through five key innovations: 1) a cloud-aware 12-dimensional RL state representation encoding CPU utilization variance, memory fragmentation, SLA violation rate, and energy metrics, 2) a composite multi-objective fitness function with adaptive weight adjustment, 3) a cloud-specific Low-Level Heuristic (LLH) pool comprising 12 operators spanning VM placement, task scheduling, and dynamic scaling, 4) an online sliding-window adaptation mechanism employing Kullback–Leibler divergence for workload shift detection and real-time policy updates, and 5) a multi-tier coordination architecture operating across infrastructure, platform, and application layers. World-CRM is evaluated on CloudSim Plus simulations with three real-world workload traces Google Cluster Trace (CCT) 2019, Azure VM Traces 2019, and bitbrains distributed data center across small (50 hosts), medium (200 hosts), and large (800 hosts) data center configurations. Results across 30 independent runs per configuration demonstrate that World-CRM achieves 23–31% energy reduction, 42–58% fewer SLA violations, 15–22% better resource utilization, and 18–27% lower makespan compared to the best-performing baselines including NSGA-II-VM, PSO-Cloud, DQN-VMPlace, Modified Best Fit Decreasing (MBFD), and the original World algorithm. The online adaptation module maintains performance under workload shifts with decision latency below 300 milliseconds and enables 3–4× faster recovery compared to RL and evolutionary baselines. All improvements are statistically significant under the Wilcoxon rank-sum test with Bonferroni correction at p < 0.05.