List your company

Comprehensive Molecule Optimization on TOMG-Bench MOLOPT (test)

19.77LogP SR × SimActive-GRPO
11.91813.956515.99518.0335Jul 1, 2026

Evaluation results

MethodLinks
Active-GRPOHardware=40GB-A100, Seeds=3, Mechanism=Active imitate-reinforce and active referencing2026.0719.7719.0414.417.73
Offline-strengthened RePOHardware=40GB-A100, Seeds=3, Reference Type=Stronger fixed target2026.0719.7418.5311.316.52
Iterative SFTHardware=40GB-A100, Seeds=3, Mechanism=Self-distillation without active policy improvement2026.0718.8817.3612.5716.27
RePOHardware=40GB-A100, Seeds=3, Reference Type=Fixed-reference baseline2026.0718.7718.612.5816.65
Zero-shotHardware=40GB-A100, Seeds=1, Evaluation Mode=Zero-shot2026.071713.1411.1413.76
GRPO-onlyHardware=40GB-A100, Seeds=3, Training Strategy=GRPO without answer-level guidance2026.0712.229.566.999.59