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.
Figures & tables
Figure 1. Overview of MobilityBench, a systematic benchmark for evaluating route-planning agents.
Intent Family
Task Scenario
Example Query
Basic Information Retrieval
POI Query
Where is the gas station?
Geolocation Query
Where am I?
Nearby Query
Search for restaurants near Beijing Capital International Airport.
Weather Query
What is the weather like in Wuhan tomorrow?
Traffic Info Query
Is there a traffic jam on Chengdu Avenue right now?
Route-Dependent Information Retrieval
Route Property Query
How far is it from Hefei to Huangshan?
Table 1. Overview of task scenarios in MobilityBench, grouped by intent family.
Figure 2. Global coverage of MobilityBench Data.
Table 2. Performance of models on MobilityBench. Abbreviations: Instr. Und. for Instruction Understanding; Dec. Mak. for Decision Making; ID for Intent Detection; IE for Information Extraction; DEC for Task Decomposition; TS for Tool Selection; SC for Schema Compliance; DR for Delivery Rate; FPR for Final Pass Rate; IT for Input Token; and OT for Output Token.
Mobile planning requires a central agent to coordinate tools, persistent user context, reusable procedures, and specialized sub-agents while adapting to execution feedback. Evaluating these workflows requires distinguishing task completion from compliance with prescribed resource and procedural requirements. We introduce MobilePA-Bench, a benchmark comprising 1,705 tasks across eight query task domains and 212 mobile tools in a stateful simulated environment. It combines three features: (1) unified capability coverage, profiling Tool Use, Memory Usage, Skill Usage, and Sub-agent Collaboration under a common mobile protocol; (2) evidence-aligned verification, matching each task to a fixed tool-call, state-change, or interaction-behavior checker rather than imposing one completion criterion on all tasks; and (3) capability-gated evaluation, requiring task completion alongside prescribed memory checks and, in skill-only routing, complete route loading before business-tool use. With MobilePA-Bench, we systematically evaluate open- and closed-weight LLMs, revealing capability-specific weaknesses in complex mobile task execution. Fine-grained analyses distinguish failures in resource retrieval and procedural compliance from downstream execution errors, providing diagnostic insights beyond aggregate task-success rates. We further train a Qwen3.8-27B baseline with online reinforcement learning in the sandbox, whose improved performance provides initial evidence of the environment's utility for planner development.
Interactive travel planning has become a popular use case for language models. Agents are deployed to manage evolving preferences and unexpected disruptions over multiple turns. Such settings require models to make complex, profile-conditioned planning decisions. However, existing benchmarks often evaluate feasibility, personalization, or interaction in relatively isolated settings. We therefore introduce Trip+ to measure the ability of agents to plan travel holistically. In Trip+, given traveler profiles and dynamic interactions, agents must generate and revise minute-level itineraries. End-to-end traveler experiences are evaluated via an LLM-based simulator, enabling the assessment of subjective metrics like fatigue. Our scenarios range from simple request resolutions to complex environment-driven replanning. We evaluate 18 LMs and find a consistent gap in experiential quality. Models favor technically feasible but exhausting itineraries that diverge sharply from profiled traveler preferences.
The development of Large Language Models (LLMs) has significantly improved travel planning applications, yet evaluating such models is limited by existing benchmarks' limitations: 1) overemphasis on constraint compliance, neglecting multi-dimensional qualities like spatio-temporal cost; 2) datasets lacking real-world authenticity and coverage in key areas (e.g., lodging, transport); and 3) isolated daily plan assessments that miss critical details (e.g., the impact of daily accommodation and visit pacing) needed for entire plan's evaluation. To address this gap, we introduce TravelEval, a realistic and comprehensive benchmark. TravelEval features 1) a novel six-dimensional evaluation framework to holistically assess plans across accuracy, compliance, temporality, spatiality, economy, and utility dimensions; 2) a highly realistic data sandbox with precise accommodation pricing and authentic intercity transportation data; and 3) a simulation-based global evaluation method that emulates complete travel plans with API-integrated geographic information and fine-grained queuing time. Evaluating 12 mainstream approaches with TravelEval reveals several valuable insights, such that LLMs struggle with globally-optimized multi-dimensional planning (especially in spatio-temporal reasoning and budget compliance), and agentic reasoning strategies offer no consistent improvement. Concisely, TravelEval facilitates travel plan evaluation via grounded spatio-temporal emulation and comprehensive metrics, providing a robust foundation for advancing LLM-powered travel planning research and applications.
Weiyi Chen, Shuaixiong Wang, Ziyun Gao +5
Zhejiang University · Hangzhou, China · Hong Kong Polytechnic University +5