Abstract
Microwave-absorbing materials (MAM) are important for modern technologies, but the design of MAM remains hindered by insufficient experimental characterization of the microscopic mechanisms governing electromagnetic (EM) energy dissipation. While Density Functional Theory (DFT) provides theoretical evidence for probing electronic structures, its application faces significant challenges. These include discrepancies between theoretical models and realistic structures, inadequate treatment of alternating EM fields, and errors in strongly correlated systems. Recent advances in Artificial Intelligence (AI) offer transformative opportunities to address these challenges. AI algorithms can predict and model electronic responses under physical equation constraints, accelerate the screening of computational parameters, and enhance the reliability of DFT-based interpretations. This perspective critically illustrates the current state of DFT applications and the limitations of existing approaches in MAM, while analyzing contemporary strategies to mitigate DFT limitations. In addition, it is proposed prospectively that future research should integrate physics-informed neural networks, adaptive algorithms, and DFT to address the current dilemma. This not only emphasizes the transformative potential of AI but also unlocks scalable design principles for the next generation of MAM.