一作ACL 2026Poster· Natural Language Processing
A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage
Congmin Zheng · Jiachen Zhu · Zhuoying Ou · Yuxiang Chen · Kangning Zhang · Rong Shan · Zeyu Zheng · Mengyue Yang · Ruiming Tang (Huawei Noah' · s Ark Lab) · Ruiming Tang (Huawei Noah'
摘要
Large Language Models (LLMs) have advanced reasoning ability, yet conventional alignment remains dominated by outcome reward models (ORMs) that judge only final answers. Process Reward Models(PRMs) address this gap by evaluating and guiding reasoning at the step or trajectory level. This survey p...