AN, Zhiyu; DU, Wan. MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 37232–37239, 2026. DOI: 10.1609/aaai.v40i44.41054. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41054. Acesso em: 9 may. 2026.