@article{rotbenchamultilevelbenchmarkfor,
  title = {RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning},
  author = {Junjie Ye and Yilong Wu and Songyang Gao and Caishuang Huang and Sixian Li and Guanyu Li and Xiaoran Fan and Qi Zhang and Tao Gui and Xuanjing Huang},
  year = {2024},
  eprint = {2401.08326},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.08326v3},
}