@article{benchmarkingreasoningrobustnessinlarge,
  title = {Benchmarking Reasoning Robustness in Large Language Models},
  author = {Tong Yu and Yongcheng Jing and Xikun Zhang and Wentao Jiang and Wenjie Wu and Yingjie Wang and Wenbin Hu and Bo Du and DaCheng Tao},
  year = {2025},
  eprint = {2503.04550},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.04550v1},
}