#6 - rStar-Math: Self-Evolved Deep Thinking for Math Reasoning

The paper introduces rStar-Math, a novel method that significantly improves the mathematical reasoning capabilities of small language models (SLMs). It achieves this through a self-evolving process using Monte Carlo Tree Search (MCTS) and three key innovations: code-augmented data synthesis, a novel process preference model (PPM) training method, and a four-round self-evolution recipe. rStar-Math surpasses the performance of larger models on several challenging benchmarks, including the USA Math Olympiad (AIME). The results demonstrate the potential of SLMs to achieve state-of-the-art performance in mathematical reasoning through iterative self-improvement.