Zhu, Xinxin, Ying He, Haowen Hou, Ruichong Zhang, Nianbo Zeng, Yulin Peng, Jiongfeng Fang, and F. Richard Yu. 2026. “PSPO: Prompt-Level Prioritization and Experience-Weighted Smoothing for Efficient Policy Optimization”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (34):29186-94. https://doi.org/10.1609/aaai.v40i34.40157.