LLaMA-Berry: Pairwise Optimization for Olympiad-Level Math Reasoning
On November 24, a paper titled “LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search” was published by researchers from Fudan University, Shanghai AI Lab, UC Merced, Hong Kong Polytechnic, University of New South Wales, Shanghai Jiao Tong University, and Stanford University. This paper proposes a mathematical reasoning framework called LLaMA-Berry … Read more