Forest-of-Thought：扩展测试时计算以增强LLM推理
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
AI总结：
针对LLM单次推理无法纠错的问题，提出Forest-of-Thought框架，通过集成多推理树、稀疏激活、动态自纠正和共识引导决策，显著提升了模型解决复杂推理任务的精度与效率。
摘要：
大型语言模型（LLMs）在各种语言任务中展现了卓越的能力，但解决复杂推理问题仍是一项重大挑战。虽然现有方法（如Chain-of-Thought (CoT)和Tree-of-Thought (ToT)）通过分解问题或构建提示来增强推理，但它们通常只执行单次推理，可能无法重新审视有缺陷的路径，从而影响准确性。为解决这一局限性，我们提出了一种名为Forest-of-Thought (FoT)的新型推理框架，该框架集成多棵推理树，利用集体决策来解决复杂逻辑问题。FoT采用稀疏激活策略选择最相关的推理路径，同时提高了效率和准确性。此外，我们引入了支持实时纠错的动态自纠正策略，以及优化正确性和计算资源的共识引导决策策略。实验结果表明，FoT框架结合这些策略显著增强了LLMs的推理能力，使其能够以更高的精度和效率解决复杂任务。代码将发布于https://github.com/iamhankai/Forest-of-Thought。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
