@article{balancedactorinitializationstablerlhftra, title = {Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models}, author = {Chen Zheng and Yiyuan Ma and Yuan Yang and Deyi Liu and Jing Liu and Zuquan Song and Yuxin Song and Cheng Ren and Hang Zhu and Xin Liu and Yiyuan Ma and Siyuan Qiao and Xun Zhou and Liang Xiang and Yonghui Wu}, year = {2025}, eprint = {2509.00309}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.00309}, }