HAHM, Dongyoon; MIN, Taywon; JIN, Woogyeol; LEE, Kimin. Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 37443–37451, 2026. DOI: 10.1609/aaai.v40i44.41077. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41077. Acesso em: 25 may. 2026.