We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works often overlooked its biggest drawback--slower speed compared to CoT; 2. Previous research mainly used MCTS as a tool for LLM reasoning on various tasks with limited quantitative analysis or ablation studies of its components from reasoning interpretability perspective. 3. The reward model is the most crucial component in MCTS, however previous work has rarely conducted in-depth study or improvement of MCTS's reward models. Thus, we conducted extensive ablation studies and quantitative analysis on components of MCTS, revealing the impact of each component on the MCTS reasoning performance of LLMs. Building on this, (i) we designed a highly interpretable reward model based on the principle of contrastive decoding and (ii) achieved an average speed improvement of 51.9% per node using speculative decoding. Additionally, (iii) we improved UCT node selection strategy and backpropagation used in previous works, resulting in significant performance improvement. We outperformed o1-mini by an average of 17.4% on the Blocksworld multi-step reasoning dataset using Llama-3.1-70B with SC-MCTS*.

翻译：我们提出SC-MCTS*：一种用于大语言模型（LLM）的新型蒙特卡洛树搜索（MCTS）推理算法，显著提升了推理准确性与速度。我们的研究动机源于：1. 先前基于MCTS的LLM推理工作常忽视其最大缺陷——与思维链（CoT）方法相比速度较慢；2. 既往研究主要将MCTS作为LLM在多任务上的推理工具，缺乏从推理可解释性角度对其组件进行定量分析或消融研究；3. 奖励模型是MCTS中最关键的组件，但已有工作很少对MCTS的奖励模型进行深入研究或改进。为此，我们对MCTS各组件开展了系统的消融实验与定量分析，揭示了各组件对LLM的MCTS推理性能的影响。基于此，（i）我们依据对比解码原理设计了一个高可解释性的奖励模型；（ii）通过推测解码技术实现了单节点平均51.9%的速度提升；（iii）我们改进了先前工作中使用的UCT节点选择策略与反向传播机制，从而带来显著的性能提升。在Blocksworld多步推理数据集上，采用Llama-3.1-70B模型结合SC-MCTS*的方法，我们的平均性能超越o1-mini模型达17.4%。