Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial aspect of human cognition, remain relatively unexplored. Human possess a remarkable ability to create mental images of unseen objects and actions through a process known as \textbf{the Mind's Eye}, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (\textbf{VoT}) prompting. VoT aims to elicit spatial reasoning of LLMs by visualizing their reasoning traces, thereby guiding subsequent reasoning steps. We employed VoT for multi-hop spatial reasoning tasks, including natural language navigation, visual navigation, and visual tiling in 2D grid worlds. Experimental results demonstrated that VoT significantly enhances the spatial reasoning abilities of LLMs. Notably, VoT outperformed existing multimodal large language models (MLLMs) in these tasks. While VoT works surprisingly well on LLMs, the ability to generate \textit{mental images} to facilitate spatial reasoning resembles the mind's eye process, suggesting its potential viability in MLLMs.

大型语言模型中的空间推理能力相对较少探索，在本文中，我们提出了一种名为Thought可视化的方法，通过可视化语言模型的推理轨迹来引导后续的推理步骤，实验证明Thought可视化显著增强了语言模型的空间推理能力，并且在多跳空间推理任务中表现优于现有的多模态大型语言模型。

思维可视化激发大型语言模型的空间推理