用过往推理经验生成可复用的指导路线，提升大模型多步推理能力
Guideline Forest: Retrieval-Augmented Reasoning with Branching Experience-Induced Guidelines
- 将高质量推理过程存为记忆，检索后生成结构化指导路线
- 在数学和编程任务上显著超越CoT、ReAct等主流方法
- 支持多模型协作与不同推理范式，灵活可扩展
检索增强生成（RAG）广泛用于将大语言模型（LLMs）锚定在外部知识中，但其在提升推理能力方面仍研究不足。现有方法或依赖推理时在线探索，或采用启发式监督推理路径，却无法有效积累和重用过往推理经验。本文提出Guideline Forest，一种检索增强的推理框架，显式利用经验引导多步推理。该框架将高质量、标签一致的推理轨迹作为可复用的记忆存储，针对新问题检索相关经验，并将其归纳为结构化指南，以引导推理并实现可控分支与聚合。在数学（GSM8K, MATH-500）和编程（MBPP, HumanEval）基准上的实验表明，该框架持续优于多种强基线方法，包括CoT、ReAct、ToT、FoT和AFlow。进一步分析显示，经验检索、指南诱导的多样性以及分步聚合是框架有效性的关键。此外，Guideline Forest不仅适用于单模型推理，还可推广至多样推理范式，并支持多模型协作，展现出良好的灵活性与可扩展性。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) has been widely adopted to ground large language models (LLMs) in external knowledge, yet it remains largely underexplored for improving reasoning. Existing methods either rely on online exploration during inference or heuristic supervision over reasoning trajectories, but they fail to effectively accumulate and reuse past reasoning experience. We propose Guideline Forest, a retrieval-augmented reasoning framework that explicitly leverages experience to guide multi-step reasoning. The framework stores high-quality, label-consistent reasoning traces as reusable memory, retrieves relevant experiences for new problems, and induces them into structured guidelines that steer reasoning and enable controlled branching and aggregation. Experiments on mathematical (GSM8K, MATH-500) and programming (MBPP, HumanEval) benchmarks demonstrate consistent improvements over strong reasoning baselines, including CoT, ReAct, ToT, FoT, and AFlow. Further analyses show that experience retrieval, guideline-induced diversity, and stepwise aggregation are key to the framework's effectiveness. Beyond single-model reasoning, Guideline Forest generalizes to enhance diverse reasoning paradigms and supports multi-model collaboration, highlighting its flexibility and scalability.
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。