@article{enhancingllmreasoningwithiterativedpoa, title = {Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation}, author = {Songjun Tu and Jiahao Lin and Xiangyu Tian and Qichao Zhang and Linjing Li and Yuqian Fu and Nan Xu and wei he and Xiangyuan Lan and Dongmei Jiang and Dongbin Zhao}, year = {2025}, eprint = {2503.12854}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.12854v2}, }