HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
It addresses planning challenges in LLMs for applications like travel planning, representing an incremental advance in reasoning methods.
The paper tackles complex planning tasks for large language models by proposing HyperTree Planning, a novel reasoning paradigm that uses hypertree-structured outlines to break down tasks hierarchically, achieving state-of-the-art accuracy on the TravelPlanner benchmark with a 3.6 times performance improvement over o1-preview.
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.