@article{canllmslearntoreasonrobustlyundernoisysu, title = {Can LLMs Learn to Reason Robustly under Noisy Supervision?}, author = {Shenzhi Yang and Guangcheng Zhu and Bowen Song and Sharon Li and Haobo Wang and Xing Zheng and Yingfan Ma and Zhongqi Chen and Weiqiang Wang and Gang Chen}, year = {2026}, eprint = {2604.03993}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.03993}, }