Key points are not available for this paper at this time.
Perovskite solar cells have emerged as leading photovoltaic technologies, owing to their exceptional efficiencies. However, challenges such as stability and scalable manufacturing hinder commercialization. Precursor additive engineering addresses these issues, yet the explosive growth of literature makes it difficult to efficiently utilize domain knowledge. Here, we introduce Perovskite-R1, a specialized large language model with advanced reasoning capabilities tailored for the discovery and design of perovskite precursor additives. By systematically mining and curating 1,232 high-quality scientific publications and integrating a comprehensive library of 33,269 candidate materials, we constructed a domain-specific instruction-tuning dataset. Experimental validation of several model-proposed strategies confirms their effectiveness in improving material stability and performance. Our work demonstrates the potential of domain-adapted large language models in accelerating materials discovery and provides an integrated workflow for intelligent, data-driven advancements in perovskite photovoltaic research. Perovskite solar cells promise high efficiency but face hurdles in stability and scalable production, complicating their commercialization. Here, the authors introduce Perovskite-R1, a large language model designed to enhance precursor additive discovery, which is validated by experimental confirmation of improved material stability and performance, providing an integrated workflow for intelligent, data-driven advancements in perovskite photovoltaics.
Wang et al. (Tue,) studied this question.