Reason from Future: Reverse Thought Chain Enhances LLM Reasoning

TL;DR

The paper introduces Reason from Future (RFF), a bidirectional reasoning paradigm for large language models that improves accuracy and efficiency by combining top-down planning with bottom-up reasoning, addressing local optima and search space issues.

Contribution

It proposes a novel reverse reasoning paradigm, RFF, that enhances LLM reasoning by integrating goal-oriented constraints and bidirectional search, surpassing traditional methods.

Findings

RFF achieves higher accuracy on complex tasks.

RFF reduces reasoning search space.

RFF mitigates error accumulation in reasoning.

Abstract

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.