@article{blendingsupervisedandreinforcementfinetu, title = {Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling}, author = {Zeyu Huang and Tianhao Cheng and Zihan Qiu and Zili Wang and Yinghui Xu and Edoardo M. Ponti and Ivan Titov}, year = {2025}, eprint = {2507.01679}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.01679}, }