@misc{zhang2026evalresearchbench,
  title         = {EvalResearchBench: Can AI Agents Design Their Own Evaluations?},
  author        = {Yaolun Zhang and Tianyi Xu and Yujie Zhao and Jishen Zhao and Qingyun Wu and Huazheng Wang},
  year          = {2026},
  eprint        = {2610.04184},
  archivePrefix = {arXiv},
  primaryClass  = {cs.AI},
  doi           = {10.48550/arXiv.2610.04184},
  url           = {https://arxiv.org/abs/2610.04184}
}
