@article{detectingmultiagentcollusionthroughmulti,
  title = {Detecting Multi-Agent Collusion Through Multi-Agent Interpretability},
  author = {Aaron Rose and Carissa Cullen and Sahar Abdelnabi and Philip Torr and Brandon Gary Kaplowitz and Christian Schroeder de Witt},
  year = {2026},
  eprint = {2604.01151},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.01151},
}