# DistRAG: Towards Distance-Based Spatial Reasoning in LLMs

arXiv: https://arxiv.org/abs/2506.03424 · HTML: https://mlsanity.com/paper/2506.03424/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 7 of 7)

- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://mlsanity.com/paper/2309.11206/) (2023)
- [Graph Reasoning for Question Answering with Triplet Retrieval](https://mlsanity.com/paper/2305.18742/) (2023)
- [Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions](https://mlsanity.com/paper/2502.18470/) (2025)

## Built on by (most cited first, 2 of 2)

- [Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs](https://mlsanity.com/paper/2605.05459/) (2026)
- [Graph-Enhanced Large Language Models for Spatial Search](https://mlsanity.com/paper/2606.22909/) (2026)

## Abstract (arXiv)

Many real world tasks where Large Language Models (LLMs) can be used require spatial reasoning, like Point of Interest (POI) recommendation and itinerary planning. However, on their own LLMs lack reliable spatial reasoning capabilities, especially about distances. To address this problem, we develop a novel approach, DistRAG, that enables an LLM to retrieve relevant spatial information not explicitly learned during training. Our method encodes the geodesic distances between cities and towns in a graph and retrieves a context subgraph relevant to the question. Using this technique, our method enables an LLM to answer distance-based reasoning questions that it otherwise cannot answer. Given the vast array of possible places an LLM could be asked about, DistRAG offers a flexible first step towards providing a rudimentary `world model' to complement the linguistic knowledge held in LLMs.