反向推理让大模型更高效解题，减少试错空间
Reason from Future: Reverse Thought Chain Enhances LLM Reasoning
- 从目标反推逻辑路径，结合上下文双向思考
- 复杂任务准确率提升，搜索空间缩小近半
- 适合需要深度推理的数学与逻辑题
已有研究表明，精心设计的推理范式如思维链（Chain-of-Thought, CoT）和思维树（Tree-of-Thought, ToT）能通过细致思考和广泛搜索提升小语言模型的推理能力。然而，无限制的分支因子导致推理开销巨大，且模型易陷入局部最优，缺乏全局视角。本文提出一种新范式——未来推理（Reason from Future, RFF），通过双向推理融合自上而下的规划与自下而上的积累。RFF的核心是反向推理机制，优先关注核心逻辑关系，并对中间步骤施加目标导向约束，从而缩减搜索空间，缓解顺序前向推理中的错误累积。在多种实验中，RFF展现出更高的准确性与更低的搜索开销，显著优于传统范式。
原文摘要 · Abstract (English)
It has been demonstrated that carefully designed reasoning paradigms, like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), can enhance the reasoning capabilities of small language models by detailed thinking and extensive thought searching, unbounded branching factors in the searching space create prohibitive reasoning consumption. However these methods fall into the trap of local optimum reasoning, which means the model lacks a global perspective while solving problems. We propose a novel reasoning paradigm called Reason from Future (RFF), which generates reasoning paths by bidirectional reasoning that combines top-down planning with bottom-up reasoning accumulation. The essence of RFF lies in its reverse reasoning mechanism, which prioritizes core logical relationships and imposes goal-oriented constraints on intermediate steps, thereby reducing the searching space and mitigating error accumulation inherent in sequential forward reasoning. Empirical evaluations across diverse experiments demonstrate that RFF outperforms conventional paradigms with higher accuracy and less searching space to solve complex tasks.
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。