Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures

Abstract

We introduce GSU, a text-only grid dataset to evaluate the spatial reasoning capabilities of LLMs over 3 core tasks: navigation, object localization, and structure composition. By forgoing visual inputs, isolating spatial reasoning from perception, we show that while most models grasp basic grid concepts, they struggle with frames of reference relative to an embodied agent and identifying 3D shapes from coordinate lists. We also find that exposure to a visual modality does not provide a generalizable understanding of 3D space that VLMs are able to utilize for these tasks. Finally, we show that while the very latest frontier models can solve the provided tasks (though harder variants may still stump them), fully fine-tuning a small LM or LORA fine-tuning a small LLM show potential to match frontier model performance, suggesting an avenue for specialized embodied agents.

Figures (3)

• Figure 1: The GSU Dataset tasks and settings visualized for clarity (note that the models do NOT receive these visuals and instead receive a textual version of the environment shown in Appendix \ref{['sec:appendix']}). The grey arrows indicate the heading, i.e. direction that the embodied agent is facing. In the Navigation task, they remain aligned with +Y in the Cardinal setting and rotate to reflect the last direction of travel in the Egocentric setting, which affects the direction of the second step and the final coordinates. For the Object Localization task, we show how different headings affect the spatial relations between the target and the reference. For the Structure Composition task, we show the 3 structure categories that models may be asked to describe.
• Figure 2: Allocentric front/back flipping
• Figure 3: GSU Dataset Tasks and Settings