ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning
Published in Transactions on Machine Learning Research (TMLR 2026), 2026
Recommended citation: Ziwen Wang, Jiajun Fan, Ruihan Guo, Thao Nguyen, Heng Ji, Ge Liu. "ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning." Transactions on Machine Learning Research (TMLR), 2026. https://arxiv.org/abs/2506.07459
We propose ProteinZero, a self-improving framework for protein generation via online reinforcement learning. The model iteratively improves its own protein design capabilities without human-curated data, demonstrating how RL-based self-evolution can be extended to biological sequence generation.