In pharmaceutical sciences, the use of Artificial Intelligence (AI) in excipient engineering has become a paradigm shift that makes it possible to rationally develop, optimize, and customize medication formulations. Once considered inert carriers, traditional excipients are now being rethought as intelligent substances that can affect solubility, permeability, metabolism, and therapeutic effectiveness. In order to forecast excipient–Active Pharmaceutical Ingredient (API) compatibility, modify ADMET profiles, and direct formulation methods in a target-specific and patient-centric manner, this paper examines the use of Machine Learning (ML), deep learning, and computational modeling. Important Artificial Intelligence (AI) techniques, including QSAR models, neural networks, and predictive simulations, are speeding up formulation development, improving safety profiles, and enabling virtual screening of novel excipients. Excipient-based systems are also being revolutionized by Industry 4.0's integration of digital twins, high-throughput in silico screening platforms, and real-time production analytics. Furthermore, we will illustrate how AI-aided formulation design can facilitate optimization of leads, identify synergistic excipients, and overcome challenges of toxicity, stability, and scalability. Finally, we will address issues related to translation, including ethics, validation, and regulatory requirements, emphasizing the importance of interdisciplinary collaboration to maximize the true potential of AI in pharmaceutical formulation research. For the adoption of AI-excipient technologies for next-generation therapy, this study offers a unified platform for researchers and industry professionals.
Chauhan et al. (2026) studied this question.