Huang, Baixiang, Zhen Tan, Haoran Wang, Zijie Liu, Dawei Li, Ali Payani, Huan Liu, Tianlong Chen, and Kai Shu. 2026. “Model Editing As a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (37):31113-21. https://doi.org/10.1609/aaai.v40i37.40372.