Fang, Zhanhong, Debing Wang, Jinbiao Chen, Jiahai Wang, and Zizhen Zhang. “UCPO: A Universal Constrained Combinatorial Optimization Method via Preference Optimization”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 43 (March 14, 2026): 36900–36908. Accessed May 15, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/41017.