Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Spatial Reasoning Questions

Spatial reasoning remains a challenge for Large Language Models (LLMs), which struggle with spatial data retrieval and reasoning. We propose Spatial Retrieval-Augmented Generation (Spatial-RAG), a framework that extends RAG to spatial tasks by integrating sparse spatial retrieval (spatial databases) and dense semantic retrieval (LLM-based similarity). A multi-objective ranking strategy balances spatial constraints and semantic relevance, while an LLM-guided generator ensures coherent responses. Experiments on a real-world tourism dataset show that Spatial-RAG significantly improves spatial question answering, bridging the gap between LLMs and spatial intelligence.

@article{yu2025_2502.18470,
  title={ Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Spatial Reasoning Questions },
  author={ Dazhou Yu and Riyang Bao and Gengchen Mai and Liang Zhao },
  journal={arXiv preprint arXiv:2502.18470},
  year={ 2025 }
}