Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

Maya Pavlova, Erik Brinkman, Krithika Iyer, Vítor Albiero, Joanna Bitton +4 more
2/14/2026

No official code found. Best implementation: kshishanova/GOAT_project (0 stars, last commit 2026-03-14).

Semantic Scholar

Code Implementations(1)

kshishanova/GOAT_projectCommunity71%

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

00PythonNov 18, 20257 months ago

Cite this paper

@article{pavlova2026automated,
  title  = {Automated Red Teaming with GOAT: the Generative Offensive Agent Tester},
  author = {Maya Pavlova and Erik Brinkman and Krithika Iyer and Vítor Albiero and Joanna Bitton and Hailey Nguyen and Cristian Canton Ferrer and Ivan Evtimov and Aaron Grattafiori},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:9151b11db741ab63bceaba33a5a5cc6673b5f9f8},
  journal = {ICML 2025 2025}
}

Discussion