HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking

Runquan Gui, Zhihai Wang, Jie Wang, Chi Ma, Huiling Zhen, Mingxuan Yuan, Jianye Hao, Defu Lian, Enhong Chen, Feng Wu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20694-20722, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-gui25b, title = {{H}yper{T}ree Planning: Enhancing {LLM} Reasoning via Hierarchical Thinking}, author = {Gui, Runquan and Wang, Zhihai and Wang, Jie and Ma, Chi and Zhen, Huiling and Yuan, Mingxuan and Hao, Jianye and Lian, Defu and Chen, Enhong and Wu, Feng}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {20694--20722}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/gui25b/gui25b.pdf}, url = {https://proceedings.mlr.press/v267/gui25b.html}, 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.} }
Endnote
%0 Conference Paper %T HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking %A Runquan Gui %A Zhihai Wang %A Jie Wang %A Chi Ma %A Huiling Zhen %A Mingxuan Yuan %A Jianye Hao %A Defu Lian %A Enhong Chen %A Feng Wu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-gui25b %I PMLR %P 20694--20722 %U https://proceedings.mlr.press/v267/gui25b.html %V 267 %X 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.
APA
Gui, R., Wang, Z., Wang, J., Ma, C., Zhen, H., Yuan, M., Hao, J., Lian, D., Chen, E. & Wu, F.. (2025). HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:20694-20722 Available from https://proceedings.mlr.press/v267/gui25b.html.

Related Material