@article{benchguardwhoguardsthebenchmarksautomate,
  title = {BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks},
  author = {Xinming Tu and Tianze Wang and  Yingzhou and  Lu and Kexin Huang and Yuanhao Qu and Sara Mostafavi},
  year = {2026},
  eprint = {2604.24955},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.24955},
}