Abstract Artificial intelligence is increasingly capable of predicting chemical properties, generating candidate structures, and assisting experimental planning. Yet the rate-limiting step in energy and chemical innovation is no longer prediction alone: it is the conversion of computational proposals into reproducible experiments and deployable process decisions. In this Perspective, we argue that Artificial Intelligence for Science in chemistry is undergoing a decisive transition from model-centric performance improvement to executable, closed-loop research infrastructure. This transition involves three coupled layers. First, physically grounded models must connect molecular and materials structures with energetics, kinetics, experimental observations, and uncertainty. Second, design algorithms must operate in validation-aware workflows that link inverse design, mechanistic computation, experimentation, and process constraints. Third, autonomous laboratories require reusable agent infrastructure that integrates scientific software, instruments, analytical feedback, safety control, and human accountability. We discuss developments in molecular and catalyst design, reaction optimization, digital twins, and self-driving laboratories, and identify data provenance, physical execution, reliability benchmarking, and safety governance as central translational challenges. For energy and chemical engineering, the value of artificial intelligence will ultimately be determined not by the number of candidates it proposes, but by its ability to close the loop from hypothesis to validated technology.
Zhu et al. (Thu,) studied this question.