Artificial intelligence in high-entropy materials

High-entropy materials (HEMs) are a transformative class of materials exhibiting remarkable properties, making them highly attractive for demanding applications. However, their vast compositional space and complex inter-element interactions pose significant challenges for traditional development methods. The integration of artificial intelligence (AI) and machine learning (ML) with high-throughput techniques has emerged as a powerful solution, revolutionizing the discovery and optimization of HEMs. This review highlights the synergistic paradigm of AI and high-throughput methods in HEMs research. High-throughput experimental approaches enable rapid screening of multiple compositions, while complementary computational methods provide theoretical insights and accelerate predictions of material properties. Machine learning models, ranging from supervised learning to unsupervised learning offer robust tools for predicting material properties, optimizing compositions, and discovering new materials. Generative models and inverse design approaches further enable the creation of novel HEMs with desired properties. The multi - objective optimization framework provides an effective means to find the best balance among multiple performance indicators. Large language models process and integrate massive amounts of data and extract key information, providing data-driven insights for the discovery of complex materials. The integration of these techniques into a closed-loop development system enables continuous feedback between experimental data, computational predictions, and machine learning models, thereby accelerating the discovery and optimization of HEMs, which not only streamlines the exploration of vast compositional spaces but also provides multi-scale insights into material behavior. As AI continues to evolve and integrate with emerging technologies, the future of HEM research holds great promise for sustainable development and accelerate their translation from the laboratory to practical applications.