@inproceedings{arcadinho-etal-2024-automated,
    title = "Automated test generation to evaluate tool-augmented {LLM}s as conversational {AI} agents",
    author = "Arcadinho, Samuel  and
      Aparicio, David Oliveira  and
      Almeida, Mariana S. C.",
    editor = "Hupkes, Dieuwke  and
      Dankers, Verna  and
      Batsuren, Khuyagbaatar  and
      Kazemnejad, Amirhossein  and
      Christodoulopoulos, Christos  and
      Giulianelli, Mario  and
      Cotterell, Ryan",
    booktitle = "Proceedings of the 2nd GenBench Workshop on Generalisation (Benchmarking) in NLP",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.genbench-1.4/",
    doi = "10.18653/v1/2024.genbench-1.4",
    pages = "54--68"
}