andriushchenko-2024-agentharm:
  type: article
  title: 'AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents'
  author:
  - Andriushchenko, Maksym
  - Souly, Alexandra
  - Dziemian, Mateusz
  - Duenas, Derek
  - Lin, Maxwell
  - Wang, Justin
  - Hendrycks, Dan
  - Zou, Andy
  - Kolter, Zico
  - Fredrikson, Matt
  - Winsor, Eric
  - Wynne, Jerome
  - Gal, Yarin
  - Davies, Xander
  date: 2025
  serial-number:
    arxiv: '2410.09024'
  parent:
    type: proceedings
    title: The Thirteenth International Conference on Learning Representations (ICLR 2025)
