TravelPlanner is a benchmark dataset designed for evaluating the complex planning capabilities of language agents under tool usage and multi-constraint conditions. It was released in 2024 by researchers from Fudan University, Ohio State University, Pennsylvania State University, and Meta AI. The related paper results are "TravelPlanner: A Benchmark for Real-World Planning with Language Agents".

The dataset contains 1,225 carefully curated planning intentions and reference plans, designed to test the planning capabilities of language agents in real-world scenarios. The dataset is based on travel planning and requires language agents to generate a comprehensive travel plan based on a given query, including transportation, daily meals, attractions, and accommodation.