P PaperCompassAI 论文工作台
← 返回论文检索
KDD 2026Research Track

AURORA: Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification.

Xiaoyu Tan, Tianchu Yao, Chao Qu, Bin Li 0091, Minghao Yang, Dakuan Lu, Haozhe Wang 0002, Yinghui Xu 0001, Xihe Qiu

论文页面 ↗ 登录后记笔记

PDF 由论文原始站点提供，PaperCompass 不保存论文文件。DOI 10.1145/3770854.3780168 ↗

摘要

该来源暂未提供摘要。