@inproceedings{luo-etal-2026-jaggedbench,
    title = "{J}agged{B}ench: Measuring Reasoning Invariance via Automated Weakness Exploration",
    author = "Luo, Donghao  and
      Zhang, Chenchen  and
      Li, Siheng  and
      Xu, Zenan  and
      Yi, Qi  and
      Boyuqiu  and
      Wang, Weikang  and
      Huang, Guanhua  and
      Yang, Tao  and
      Zhou, Bo  and
      Chan, Alex",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1145/",
    pages = "24240--24279",
    ISBN = "979-8-89176-462-0"
}