Reproduce “APOLLO: An Optimized Training Approach for Long-form Numerical 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
Jiashuo Sun, Hang Zhang, Chen Lin, Xiangdong Su, Yeyun Gong, Jian Guo
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.