@article{thinkbenchdynamicoutofdistribution, title = {ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning}, author = {Shulin Huang and Linyi Yang and Yan Song and Shuang Chen and Leyang Cui and Ziyu Wan and Qingcheng Zeng and Ying Wen and Kun Shao and Weinan Zhang and Jun Wang and Yue Zhang}, year = {2025}, eprint = {2502.16268}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.16268v1}, }