HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gui, Runquan, Wang, Zhihai, Wang, Jie, Ma, Chi, Zhen, Huiling, Yuan, Mingxuan, Hao, Jianye, Lian, Defu, Chen, Enhong, Wu, Feng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912400493510656
author Gui, Runquan
Wang, Zhihai
Wang, Jie
Ma, Chi
Zhen, Huiling
Yuan, Mingxuan
Hao, Jianye
Lian, Defu
Chen, Enhong
Wu, Feng
author_facet Gui, Runquan
Wang, Zhihai
Wang, Jie
Ma, Chi
Zhen, Huiling
Yuan, Mingxuan
Hao, Jianye
Lian, Defu
Chen, Enhong
Wu, Feng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02322
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
Gui, Runquan
Wang, Zhihai
Wang, Jie
Ma, Chi
Zhen, Huiling
Yuan, Mingxuan
Hao, Jianye
Lian, Defu
Chen, Enhong
Wu, Feng
Artificial Intelligence
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.
title HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
topic Artificial Intelligence
url https://arxiv.org/abs/2505.02322