Research

Paper

AI LLM February 26, 2026

MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios

Authors

Zhiheng Song, Jingshuai Zhang, Chuan Qin, Chao Wang, Chao Chen, Longfei Xu, Kaikui Liu, Xiangxiang Chu, Hengshu Zhu

Abstract

Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is hindered by diverse routing demands, non-deterministic mapping services, and limited reproducibility. In this study, we introduce MobilityBench, a scalable benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios. MobilityBench is constructed from large-scale, anonymized real user queries collected from Amap and covers a broad spectrum of route-planning intents across multiple cities worldwide. To enable reproducible, end-to-end evaluation, we design a deterministic API-replay sandbox that eliminates environmental variance from live services. We further propose a multi-dimensional evaluation protocol centered on outcome validity, complemented by assessments of instruction understanding, planning, tool use, and efficiency. Using MobilityBench, we evaluate multiple LLM-based route-planning agents across diverse real-world mobility scenarios and provide an in-depth analysis of their behaviors and performance. Our findings reveal that current models perform competently on Basic information retrieval and Route Planning tasks, yet struggle considerably with Preference-Constrained Route Planning, underscoring significant room for improvement in personalized mobility applications. We publicly release the benchmark data, evaluation toolkit, and documentation at https://github.com/AMAP-ML/MobilityBench .

Metadata

arXiv ID: 2602.22638
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-26
Fetched: 2026-02-28 05:45

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22638v1</id>\n    <title>MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios</title>\n    <updated>2026-02-26T05:39:38Z</updated>\n    <link href='https://arxiv.org/abs/2602.22638v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22638v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is hindered by diverse routing demands, non-deterministic mapping services, and limited reproducibility. In this study, we introduce MobilityBench, a scalable benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios. MobilityBench is constructed from large-scale, anonymized real user queries collected from Amap and covers a broad spectrum of route-planning intents across multiple cities worldwide. To enable reproducible, end-to-end evaluation, we design a deterministic API-replay sandbox that eliminates environmental variance from live services. We further propose a multi-dimensional evaluation protocol centered on outcome validity, complemented by assessments of instruction understanding, planning, tool use, and efficiency. Using MobilityBench, we evaluate multiple LLM-based route-planning agents across diverse real-world mobility scenarios and provide an in-depth analysis of their behaviors and performance. Our findings reveal that current models perform competently on Basic information retrieval and Route Planning tasks, yet struggle considerably with Preference-Constrained Route Planning, underscoring significant room for improvement in personalized mobility applications. We publicly release the benchmark data, evaluation toolkit, and documentation at https://github.com/AMAP-ML/MobilityBench .</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-26T05:39:38Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Zhiheng Song</name>\n    </author>\n    <author>\n      <name>Jingshuai Zhang</name>\n    </author>\n    <author>\n      <name>Chuan Qin</name>\n    </author>\n    <author>\n      <name>Chao Wang</name>\n    </author>\n    <author>\n      <name>Chao Chen</name>\n    </author>\n    <author>\n      <name>Longfei Xu</name>\n    </author>\n    <author>\n      <name>Kaikui Liu</name>\n    </author>\n    <author>\n      <name>Xiangxiang Chu</name>\n    </author>\n    <author>\n      <name>Hengshu Zhu</name>\n    </author>\n  </entry>"
}