ZHU, Xinxin; HE, Ying; HOU, Haowen; ZHANG, Ruichong; ZENG, Nianbo; PENG, Yulin; FANG, Jiongfeng; YU, F. Richard. PSPO: Prompt-Level Prioritization and Experience-Weighted Smoothing for Efficient Policy Optimization. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 34, p. 29186–29194, 2026. DOI: 10.1609/aaai.v40i34.40157. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40157. Acesso em: 10 may. 2026.