Clusters, an aggregation of several to thousands of atoms, molecules, or ions, are the building blocks of novel functional materials by atomic manufacturing and exhibit excellent applications in catalysis, quantum information, and nanomedicine. The evolution of cluster structures has been studied for many years. Many effective structural search methods, such as genetic algorithm, basin‐hopping, and so on, have been developed. However, the efficient execution of these methods relies on precise energy calculators, such as density functional theory (DFT) calculations. Up to now, limited by computational methods and capabilities, the researches mainly focus on free‐standing clusters, which are different from clusters in practical applications. Recently, the rapid development of big data‐driven machine learning is expected to replace DFT for high‐precision large‐scale computing. In this review, the present cluster search methods and challenges currently faced have been summarized. It is proposed that the development of artificial intelligence has the potential to solve some practical problems including the structural and properties evolution of clusters in complex environment, causing revolutionary developments in the fields of catalysis, quantum information, and nanomedicine based on clusters.