From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models

arXiv:2606.04381v1 Announce Type: cross
Abstract: Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely emphsymbolic, arising from pattern matching over spatial language rather than true emphgeometric reasoning over space. Because LLMs operate on discrete tokens, they lack native support for continuous spatial representations, explicit geometric computation, and structured spatial operators. To address this limitation, we introduce the emphSpatial Language Model (SLM), the first multimodal LLM that treats location information as a first-class modality and enables geometric spatial reasoning within the model’s inference process. SLM directly operates on learned spatial representations rather than textual descriptions of spatial relations. To support effective training, we construct a emphSpatial Instruction Dataset that aligns spatial representations, atomic geometric operations, and natural language instructions. We further propose a new benchmark named emphSpatialEval, which is designed to evaluate spatial reasoning across attributes, distance, topology, and relative-position tasks. Extensive experiments show that SLM significantly outperforms existing LLM-based approaches that rely on symbolic reasoning via prompt engineering or textual abstraction, demonstrating the benefits of integrating geometric spatial representations for robust spatial reasoning.
Our instruction dataset, evaluation benchmark, model training codes, and models’ checkpoints can be found at:
hyperlinkhttps://github.com/chuchen2017/SLMhttps://github.com/chuchen2017/SLM.