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

2025-10-01

AI Summary

This work investigates the geospatial reasoning capabilities of large language models (LLMs), specifically their ability to perform navigation solely from textual representations of road networks. To address this, we propose a novel trajectory recovery paradigm, introduce GLOBALTRACE—a benchmark dataset comprising over 4,000 real-world trajectories—and design a zero-shot prompting framework that natively integrates road network topology, coordinate systems, and multimodal traffic semantics without external tools, enabling cross-regional, multi-modal route generation. Experiments demonstrate that our framework significantly outperforms existing baselines and specialized trajectory models under zero-shot settings; it also supports flexible incorporation of user preferences to enhance navigational plausibility and practicality. Our core contributions are: (1) the first systematic evaluation of LLMs’ intrinsic geospatial reasoning capacity, and (2) a scalable, tool-free, end-to-end trajectory generation methodology.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• Evaluating LLMs' ability to interpret road networks for navigation tasks
• Developing trajectory recovery methods using real-world GPS data
• Assessing systematic biases in geospatial reasoning across regions

Innovation

• Uses road network as context for prompting
• Recovers trajectories by reconstructing masked GPS traces
• Generates valid paths without external navigation tools