@article{stressevalfailuredrivendynamicbenchmarki, title = {StressEval: Failure-Driven Dynamic Benchmarking for Knowledge-Intensive Reasoning in Large Language Models}, author = {Yongrui Chen and Yangyang Ma and Xiaoying Huang and Shenyu Zhang and Huajun Chen and Haofen Wang and Guilin Qi}, year = {2026}, eprint = {2605.01939}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.01939}, }