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

arXiv: https://arxiv.org/abs/2502.18470 · HTML: https://mlsanity.com/paper/2502.18470/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 23 of 23)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://mlsanity.com/paper/2402.07630/) (2024)
- [Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering](https://mlsanity.com/paper/2210.02627/) (2022)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [GPT4GEO: How a Language Model Sees the World's Geography](https://mlsanity.com/paper/2306.00020/) (2023)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding](https://mlsanity.com/paper/2310.14478/) (2023)
- [TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning](https://mlsanity.com/paper/2406.15658/) (2024)
- [Geographic and Geopolitical Biases of Language Models](https://mlsanity.com/paper/2212.10408/) (2022)
- [Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark](https://mlsanity.com/paper/2401.03991/) (2024)
- [Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions](https://mlsanity.com/paper/2105.09392/) (2021)
- [Do Language Models Know the Way to Rome?](https://mlsanity.com/paper/2109.07971/) (2021)
- [PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph](https://mlsanity.com/paper/2407.00742/) (2024)
- [Joint Spatio-Textual Reasoning for Answering Tourism Questions](https://mlsanity.com/paper/2009.13613/) (2020)
- [Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations](https://mlsanity.com/paper/2307.03678/) (2023)
- [RAG-based Question Answering over Heterogeneous Data and Text](https://mlsanity.com/paper/2412.07420/) (2024)
- [Text Embeddings for Retrieval From a Large Knowledge Base](https://mlsanity.com/paper/1810.10176/) (2018)
- [Large Scale Question Answering using Tourism Data](https://mlsanity.com/paper/1909.03527/) (2019)
- [Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction](https://mlsanity.com/paper/2407.00748/) (2024)
- [PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph](https://mlsanity.com/paper/2502.01814/) (2025)

## Built on by (most cited first, 13 of 13)

- [Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts](https://mlsanity.com/paper/2601.16965/) (2026)
- [DistRAG: Towards Distance-Based Spatial Reasoning in LLMs](https://mlsanity.com/paper/2506.03424/) (2025)
- [From Questions to Queries: An AI-powered Multi-Agent Framework for Spatial Text-to-SQL](https://mlsanity.com/paper/2510.21045/) (2025)
- [Real-time Spatial Retrieval Augmented Generation for Urban Environments](https://mlsanity.com/paper/2505.02271/) (2025)
- [TRACE: Tourism Recommendation with Accountable Citation Evidence](https://mlsanity.com/paper/2605.07677/) (2026)
- [Naiad: Novel Agentic Intelligent Autonomous System for Inland Water Monitoring](https://mlsanity.com/paper/2601.05256/) (2025)
- [Geography According to ChatGPT -- How Generative AI Represents and Reasons about Geography](https://mlsanity.com/paper/2603.18881/) (2026)
- [Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions](https://mlsanity.com/paper/2603.23375/) (2026)
- [Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma](https://mlsanity.com/paper/2604.07490/) (2026)
- [GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMs](https://mlsanity.com/paper/2608.00877/) (2026)
- [LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data](https://mlsanity.com/paper/2608.25039/) (2026)
- [PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery](https://mlsanity.com/paper/2609.32856/) (2026)
- [Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic Reasoning](https://mlsanity.com/paper/2609.39437/) (2026)

## Abstract (arXiv)

Answering real-world geospatial questions--such as finding restaurants along a travel route or amenities near a landmark--requires reasoning over both geographic relationships and semantic user intent. However, existing large language models (LLMs) lack spatial computing capabilities and access to up-to-date, ubiquitous real-world geospatial data, while traditional geospatial systems fall short in interpreting natural language. To bridge this gap, we introduce Spatial-RAG, a Retrieval-Augmented Generation (RAG) framework designed for geospatial question answering. Spatial-RAG integrates structured spatial databases with LLMs via a hybrid spatial retriever that combines sparse spatial filtering and dense semantic matching. It formulates the answering process as a multi-objective optimization over spatial and semantic relevance, identifying Pareto-optimal candidates and dynamically selecting the best response based on user intent. Experiments across multiple tourism and map-based QA datasets show that Spatial-RAG significantly improves accuracy, precision, and ranking performance over strong baselines.