An, Z. and Du, W. 2026. MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 44 (Mar. 2026), 37232–37239. DOI:https://doi.org/10.1609/aaai.v40i44.41054.