An Z, Du W. MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 9];40(44):37232-9. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/41054