用多条推理路径并行思考，提升大模型解题准确率
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
- 构建多个推理树，通过集体决策选择最优解法
- 动态纠错机制让模型实时修正错误路径，准确率显著提升
- 适合需要高精度逻辑推理的复杂任务场景
大型语言模型在多种语言任务中表现出色，但解决复杂推理问题仍面临挑战。现有方法如思维链（CoT）和树状思维（ToT）虽能分解问题或结构化提示，但通常仅进行单次推理，难以回溯错误路径，影响准确性。为此，我们提出新型推理框架森林思维（FoT），通过整合多条推理树，实现集体决策以解决复杂逻辑问题。FoT采用稀疏激活策略筛选最相关路径，提升效率与准确率。此外，引入动态自纠正机制实现实时纠错，并结合共识引导决策策略，在保证正确性的同时优化计算资源。实验表明，该框架显著增强大模型的推理能力，使其在复杂任务中实现更高精度与效率。代码将公开于 https://github.com/iamhankai/Forest-of-Thought。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated remarkable abilities across various language tasks, but solving complex reasoning problems remains a significant challenge. While existing methods, such as Chain-of-Thought (CoT) and Tree-of-Thought (ToT), enhance reasoning by decomposing problems or structuring prompts, they typically perform a single pass of reasoning and may fail to revisit flawed paths, compromising accuracy. To address this limitation, we propose a novel reasoning framework called Forest-of-Thought (FoT), which integrates multiple reasoning trees to leverage collective decision-making for solving complex logical problems. FoT employs sparse activation strategies to select the most relevant reasoning paths, improving both efficiency and accuracy. Additionally, we introduce a dynamic self-correction strategy that enables real-time error correction, along with consensus-guided decision-making strategies to optimize both correctness and computational resources. Experimental results demonstrate that the FoT framework, combined with these strategies, significantly enhances the reasoning capabilities of LLMs, enabling them to solve complex tasks with greater precision and efficiency. Code will be available at https://github.com/iamhankai/Forest-of-Thought.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。