<p>Community detection in complex networks, such as social and biological systems, remains a fundamental challenge in graph-based data analysis, requiring scalable and precise algorithmic solutions. Conventional approaches often struggle with computational overhead and limited robustness when addressing large-scale networks or overlapping community structures. This paper presents an advanced hybrid meta-heuristic framework that synergistically combines the whale optimization algorithm, salp swarm algorithm, and a novel cloud optimization (CO) algorithm. A modified choice function hyperheuristic is introduced to adaptively orchestrate the optimization process, optimizing the trade-off between exploration and exploitation while maintaining computational efficiency. The CO component, inspired by atmospheric particle dynamics, enhances population diversity and mitigates premature convergence, enabling the framework to effectively capture intricate network topologies. Experimental evaluations were conducted on nine real-world datasets and synthetic Lancichinetti–Fortunato–Radicchi benchmarks, with performance assessed via normalized mutual information and modularity metrics. Results demonstrate that the proposed framework achieves superior community detection accuracy and scalability compared to seven state-of-the-art methods. This approach not only advances the field of network analysis but also offers a versatile solution for tackling high-dimensional optimization problems in dynamic environments.</p>