HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking

TL;DR

HyperTree Planning (HTP) introduces a hierarchical hypertree structure for LLM reasoning, enabling better handling of complex planning tasks with multiple sub-tasks and constraints, leading to state-of-the-art results.

Contribution

The paper presents HyperTree Planning, a novel hierarchical reasoning paradigm that improves LLM planning by structuring outlines as hypertrees for better task decomposition.

Findings

Achieved state-of-the-art accuracy on the TravelPlanner benchmark.

Demonstrated a 3.6x performance improvement over previous methods.

Effectively manages complex planning with multiple sub-tasks and constraints.

Abstract

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.