@inproceedings{ijcai2026p422,
  title     = {StressEval: Failure-Driven Dynamic Benchmarking for Knowledge-Intensive Reasoning in Large Language Models},
  author    = {Chen, Yongrui and Ma, Yangyang and Huang, Xiaoying and Zhang, Shenyu and Chen, Huajun and Wang, Haofen and Qi, Guilin},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {3792--3800},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/422},
  url       = {https://doi.org/10.24963/ijcai.2026/422},
}