用分层树结构提升大模型复杂任务规划能力
HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
- 构建超树结构实现分而治之的分层思考
- 在TravelPlanner上性能比o1-preview提升3.6倍
- 适合需要多步骤规划的复杂推理场景
近期进展显著提升了大语言模型在复杂推理任务中的表现，尤其在数学与逻辑推理领域成果显著。然而，现有方法在面对复杂规划任务时仍面临挑战，主要源于推理步骤冗长、约束多样以及需处理多个独立子任务。为此，我们提出超树规划（HyperTree Planning, HTP）这一新型推理范式，通过构建超树结构的规划框架来实现高效规划。该结构使大模型能够灵活运用分而治之策略，有效分解复杂推理步骤，适应多样约束，并有条不紊地管理多个独立子任务。我们进一步设计了一个自主规划框架，通过迭代优化和扩展超树结构的规划大纲完成整个规划过程。实验表明，HTP在TravelPlanner基准测试中表现卓越，使用Gemini-1.5-Pro时达到当前最优准确率，相较o1-preview提升3.6倍。
原文摘要 · Abstract (English)
Recent advancements have significantly enhanced the performance of large language models (LLMs) in tackling complex reasoning tasks, achieving notable success in domains like mathematical and logical reasoning. However, these methods encounter challenges with complex planning tasks, primarily due to extended reasoning steps, diverse constraints, and the challenge of handling multiple distinct sub-tasks. To address these challenges, we propose HyperTree Planning (HTP), a novel reasoning paradigm that constructs hypertree-structured planning outlines for effective planning. The hypertree structure enables LLMs to engage in hierarchical thinking by flexibly employing the divide-and-conquer strategy, effectively breaking down intricate reasoning steps, accommodating diverse constraints, and managing multiple distinct sub-tasks in a well-organized manner. We further introduce an autonomous planning framework that completes the planning process by iteratively refining and expanding the hypertree-structured planning outlines. Experiments demonstrate the effectiveness of HTP, achieving state-of-the-art accuracy on the TravelPlanner benchmark with Gemini-1.5-Pro, resulting in a 3.6 times performance improvement over o1-preview.
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。