Search papers, labs, and topics across Lattice.
The authors introduce MobilityBench, a new benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios using anonymized user queries from Amap. To address reproducibility challenges, they designed a deterministic API-replay sandbox, enabling consistent evaluation by eliminating environmental variance. Experiments using MobilityBench reveal that while current LLMs perform well on basic tasks, they struggle with preference-constrained route planning, highlighting areas for future research.
LLMs can handle basic route planning, but fall apart when user preferences enter the mix, as shown by a new benchmark based on real-world queries.
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 .
DAMO