# Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery Perspective

arXiv: https://arxiv.org/abs/2510.01639 · HTML: https://mlsanity.com/paper/2510.01639/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [Dated Data: Tracing Knowledge Cutoffs in Large Language Models](https://mlsanity.com/paper/2403.12958/) (2024)
- [Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey](https://mlsanity.com/paper/2503.13502/) (2025)
- [TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation](https://mlsanity.com/paper/2502.18712/) (2025)
- [TripTailor: A Real-World Benchmark for Personalized Travel Planning](https://mlsanity.com/paper/2508.01432/) (2025)
- [MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models](https://mlsanity.com/paper/2501.00316/) (2024)
- [UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces](https://mlsanity.com/paper/2411.03859/) (2024)
- [TrajFM: A Vehicle Trajectory Foundation Model for Region and Task Transferability](https://mlsanity.com/paper/2408.15251/) (2024)
- [BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis](https://mlsanity.com/paper/2412.00953/) (2024)
- [Quantifying Geospatial in the Common Crawl Corpus](https://mlsanity.com/paper/2406.04952/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations](https://mlsanity.com/paper/2603.08954/) (2026)

## Abstract (arXiv)

We explore the geospatial reasoning capabilities of Large Language Models (LLMs), specifically, whether LLMs can read road network maps and perform navigation. We frame trajectory recovery as a proxy task, which requires models to reconstruct masked GPS traces, and introduce GLOBALTRACE, a dataset with over 4,000 real-world trajectories across diverse regions and transportation modes. Using road network as context, our prompting framework enables LLMs to generate valid paths without accessing any external navigation tools. Experiments show that LLMs outperform off-the-shelf baselines and specialized trajectory recovery models, with strong zero-shot generalization. Fine-grained analysis shows that LLMs have strong comprehension of the road network and coordinate systems, but also pose systematic biases with respect to regions and transportation modes. Finally, we demonstrate how LLMs can enhance navigation experiences by reasoning over maps in flexible ways to incorporate user preferences.