@article{automonitorbenchevaluatingthereliability,
  title = {AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor},
  author = {Shu Yang and Jingyu Hu and Tong Li and Hanqi Yan and Wenxuan Wang and Di Wang},
  year = {2026},
  eprint = {2601.05752},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.05752},
}