@inproceedings{chen-etal-2025-implicit,
    title = "From Implicit Exploration to Structured Reasoning: Guideline and Refinement for {LLM}s",
    author = "Chen, Jiaxiang  and
      Wang, Zhuo  and
      Zou, Mingxi  and
      Li, Zhucong  and
      Zhou, Zhijian  and
      Wang, Song  and
      Xu, Zenglin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.196/",
    doi = "10.18653/v1/2025.findings-emnlp.196",
    pages = "3672--3684",
    ISBN = "979-8-89176-335-7",
    abstract = "Large language models (LLMs) have advanced general-purpose reasoning, showing strong performance across diverse tasks. However, existing methods often rely on implicit exploration, where the model follows stochastic and unguided reasoning paths{---}like walking without a map. This leads to unstable reasoning paths, lack of error correction, and limited learning from past experience. To address these issues, we propose a framework that shifts from implicit exploration to structured reasoning through guideline and refinement. First, we extract structured reasoning patterns from successful trajectories and reflective signals from failures. During inference, the model follows these guidelines step-by-step, with refinement applied after each step to correct errors and stabilize the reasoning process. Experiments on the Big-Bench Hard (BBH) benchmark show that our method consistently outperforms strong baselines across diverse reasoning tasks. Analysis reveals that stepwise execution, refinement, and experience-based learning improve stability and generalization. We further explore model collaboration during refinement, offering insights into cross-model interactions. Notably, structured reasoning guided by learned instructions matches or even surpasses knowledge distilled through SFT, highlighting its scalability and effectiveness."
}