Artificial intelligence-driven materials science: Evolution, framework, dilemmas, and breakthroughs

Artificial intelligence-driven materials science (AIMS) represents a revolutionary and disruptive paradigm in materials research, promising to fundamentally break through the traditional bottlenecks of research cycles and efficiency. Historically, the evolution of materials science research paradigms from empirical trial and error, theoretical modeling, and computational simulation to the new data-driven stage has been driven by innovations in cognitive tools and methods. Currently, artificial intelligence, as a disruptive cognitive tool, is fundamentally reconstructing the core elements and interaction logic of materials science: the research process achieves intelligent iteration and full-process closed-loop; the capabilities of researchers are reshaped and teams are organized; and the depth and breadth of research objects are expanded and precise demands are locked in, thus forming a new model and paradigm for materials research. This is precisely the manifestation of the emergence and development of new quality productivity in the field of materials science. Nevertheless, China still faces bottlenecks such as multi-scale modeling, multi-modal data fusion, and model generalization in the AIMS field. These need to be overcome through solidifying the data foundation, tackling core technologies, and improving ecological support, in order to achieve a fundamental transformation of the materials science research paradigm. This study reviews the evolution and current status of research paradigms in materials science, constructs a theoretical framework for the transformation of elements in AIMS, analyzes the difficulties and bottlenecks faced by AIMS, and proposes strategic paths and strategies for promoting the development of AIMS in China, with the aim of providing theoretical and practical references for accelerating the formation of the AIMS paradigm system and fostering new material productivity.