Pawan Prakash

Using group-relative policy optimization (GRPO), this work reinforces the discrete atom-type channel of the crystal generator OMatG, whose closed-form likelihood ratio makes element choices policy actions; with a reward combining stability, novelty and diversity plus sparse-hull and single-element guards, the yield of metastable, unique and novel structures (mSUN) on LeMat-GenBench rises from 13.4% for the pretrained model to 45.5%, while the paper records how the policy exploited earlier rewards and shows that single-element repacking is counted as discovery by existing mSUN implementations.

Using group-relative policy optimization (GRPO), this work reinforces the discrete atom-type channel of the crystal generator OMatG, whose closed-form likelihood ratio makes element choices policy actions; with a reward combining stability, novelty and diversity plus sparse-hull and single-element guards, the yield of metastable, unique and novel structures (mSUN) on LeMat-GenBench rises from 13.4% for the pretrained model to 45.5%, while the paper records how the policy exploited earlier rewards and shows that single-element repacking is counted as discovery by existing mSUN implementations.