@article{beyondsfttorlprealignmentviablackboxonpo, title = {Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL}, author = {Sudong Wang and Weiquan Huang and Xiaomin Yu and Zuhao Yang and Hehai Lin and Keming Wu and Chaojun Xiao and Chen Chen and Wenxuan Wang and Beier Zhu and Yunjian Zhang and Chengwei Qin}, year = {2026}, eprint = {2604.28123}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.28123}, }