@article{stepktooptimizingmathematicalreasoning, title = {Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback}, author = {Yen-Ting Lin and Di Jin and Tengyu Xu and Tianhao Wu and Sainbayar Sukhbaatar and Chen Zhu and Yun He and Yun-Nung Chen and Jason Weston and Yuandong Tian and Arash Rahnama and Sinong Wang and Hao Ma and Han Fang}, year = {2025}, eprint = {2501.10799}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.10799v1}, }