Reason from Future: Reverse Thought Chain Enhances LLM Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Yinlong, Zheng, Yanzhao, Sun, Shuoshuo, Huang, Shuaihan, Dong, Baohua, Zhu, Hangcheng, Huang, Ruohui, Yu, Gang, Xu, Hongxia, Wu, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918045435297792
author Xu, Yinlong
Zheng, Yanzhao
Sun, Shuoshuo
Huang, Shuaihan
Dong, Baohua
Zhu, Hangcheng
Huang, Ruohui
Yu, Gang
Xu, Hongxia
Wu, Jian
author_facet Xu, Yinlong
Zheng, Yanzhao
Sun, Shuoshuo
Huang, Shuaihan
Dong, Baohua
Zhu, Hangcheng
Huang, Ruohui
Yu, Gang
Xu, Hongxia
Wu, Jian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03673
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reason from Future: Reverse Thought Chain Enhances LLM Reasoning
Xu, Yinlong
Zheng, Yanzhao
Sun, Shuoshuo
Huang, Shuaihan
Dong, Baohua
Zhu, Hangcheng
Huang, Ruohui
Yu, Gang
Xu, Hongxia
Wu, Jian
Artificial Intelligence
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.
title Reason from Future: Reverse Thought Chain Enhances LLM Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2506.03673