Navigating sparse singlet fission chemical space: an intelligent generative-predictive paradigm

Singlet fission (SF) offers a promising route to surpass the Shockley-Queisser limit by converting a photoexcited singlet exciton into two triplet excitons, thereby enhancing photovoltaic energy conversion efficiency. However, realizing efficient SF requires the stringent energetic requirements among low-lying excited states that render SF molecules intrinsically rare within the vast chemical space. This extreme sparsity presents a fundamental challenge for molecular discovery. Due to low hit rates and trial-and-error computational waste on nonviable structures, conventional high-throughput virtual screening faces significant constraints, even when accelerated by machine learning models. Here, we establish a synergistic generative-predictive framework for the targeted inverse design of SF molecules by integrating a molecular structure generator, a properties predictor and a multi-criteria validation workflow. By continuously coupling generative exploration with SF predictive models, the framework progressively enriches SF species and achieves a success rate of approximately 90% in generating molecules that satisfy the target SF energetic criteria. High-throughput evaluation of approximately 100 million generated structures with selective time-dependent density functional theory (TDDFT) validation of 1% of candidates, together with SF molecules identified during iterative generative-predictive training, yielded 283,145 synthetically accessible unique SF molecules with favorable energetics at the TDDFT level.  From this dataset, we identified a key fragment strongly associated with the requirements for SF, namely, CN([O])N(C)[O]. These findings establish an efficient route for overcoming the sparsity difficulty in SF molecular discovery and provide interpretable design principles for the development of novel excited-state functional materials.