@article{wang2026opd, title={OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation}, author={Wang, Xinpeng and Shi, Wei and Chen, Yu-Chia and Zontak, Maria and He, Yun and Pang, Richard Yuanzhe}, journal={arXiv preprint arXiv:2610.02781}, year={2026} }