QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning

Open Webpage

Yilun Kong, Hangyu Mao, Qi Zhao, Bin Zhang, Jingqing Ruan, Li Shen, Yongzhe Chang, Xueqian Wang, Rui Zhao, Dacheng Tao

Published: 2025, Last Modified: 21 Jan 2026Trans. Mach. Learn. Res. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0