Home » Authors » Guanzhi Deng, Zengyan Liu, Haibo Wang, Kuan Wu, Shing Yin Wong, Sichun Luo, Zhuoran Wang, Linqi Song

Guanzhi Deng, Zengyan Liu, Haibo Wang, Kuan Wu, Shing Yin Wong, Sichun Luo, Zhuoran Wang, Linqi Song

Public reference bibliography and cataloged PDF materials authored or published by Guanzhi Deng, Zengyan Liu, Haibo Wang, Kuan Wu, Shing Yin Wong, Sichun Luo, Zhuoran Wang, Linqi Song.

Found 1 document(s) Page 1 of 1

A Strong MoE Is All You Need for Process Supervision

Year: 2026 • Source: arxiv.org • Listed PDF

Process reward models (PRMs) provide fine-grained supervision for multi-step reasoning, yet obtaining reliable process labels remains a central bottleneck. Existing approaches typically rely on human annotation, rollout-...