An, Zhiyu, and Wan Du. “MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 44, Mar. 2026, pp. 37232-9, doi:10.1609/aaai.v40i44.41054.