A fundamental problem in organic chemistry is identifying and predicting the series of reactions that synthesize a desired target product molecule. Due to the combinatorial nature of the chemical search space, single-step reactant prediction -- i.e. single-step retrosynthesis -- remains challenging even for existing state-of-the-art template-free generative approaches to produce an accurate yet diverse set of feasible reactions. In this paper, we model single-step retrosynthesis planning and introduce RETRO SYNFLOW (RSF) a discrete flow-matching framework that builds a Markov bridge between the prescribed target product molecule and the reactant molecule. In contrast to past approaches, RSF employs a reaction center identification step to produce intermediate structures known as synthons as a more informative source distribution for the discrete flow. To further enhance diversity and feasibility of generated samples, we employ Feynman-Kac steering with Sequential Monte Carlo based resampling to steer promising generations at inference using a new reward oracle that relies on a forward-synthesis model. Empirically, we demonstrate \nameshort achieves 60.0% top-1 accuracy, which outperforms the previous SOTA by 20%. We also substantiate the benefits of steering at inference and demonstrate that FK-steering improves top-5 round-trip accuracy by 19% over prior template-free SOTA methods, all while preserving competitive top-k accuracy results.
@article{arxiv.2506.04439,
title = {RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis},
author = {Robin Yadav and Qi Yan and Guy Wolf and Avishek Joey Bose and Renjie Liao},
journal= {arXiv preprint arXiv:2506.04439},
year = {2026}
}