@inproceedings{xu-etal-2025-reason,
    title = "Reason from Future: Reverse Thought Chain Enhances {LLM} Reasoning",
    author = "Xu, Yinlong  and
      Zheng, Yanzhao  and
      Sun, Shuoshuo  and
      Huang, Shuaihan  and
      Dong, Baohua  and
      Hangcheng, Zhu  and
      Huang, Ruohui  and
      Yu, Gang  and
      Xu, Hongxia  and
      Wu, Jian",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.findings-acl.1290/",
    doi = "10.18653/v1/2025.findings-acl.1290",
    pages = "25153--25166",
    ISBN = "979-8-89176-256-5",
    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 fell 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."
}