Zhu X, He Y, Hou H, Zhang R, Zeng N, Peng Y, et al. PSPO: Prompt-Level Prioritization and Experience-Weighted Smoothing for Efficient Policy Optimization. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 10];40(34):29186-94. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40157