Reproduce “CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Congmin Zheng, Jiachen Zhu, Jianghao Lin, Xinyi Dai, Weiwen Liu, Haoxuan Li, Yong Yu, Weinan Zhang and 1 more
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.