作者位次 #3/9KDD 2026Oral· Knowledge Discovery & Data Mining
POLO: Preference-Guided Multi-Turn Reinforcement Learning for Sample-Efficient Lead Optimization
Ziqing Wang · Yibo Wen · William Pattie · Xiao Luo · Weimin Wu · Jerry Yao-Chieh Hu · Abhishek Pandey · Han Liu · Kaize Ding