Wang, X., Shi, W., Chen, Y. C., Zontak, M., He, Y., & Pang, R. Y. (2026). OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation. https://omanscience.com/en/articles/opd-before-rl-warm-starting-rubric-based-rl-with-on-policy-distillation