@article{tasksuccessisnotenoughinvestigatingthe,
  title = {Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors},
  author = {Lin Guan and Yifan Zhou and Denis Liu and Yantian Zha and Heni Ben Amor and Subbarao Kambhampati},
  year = {2024},
  eprint = {2402.04210},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.04210v2},
}