Dataset · osunlp
Travel planning benchmark
osunlp/TravelPlanner
1,225 queries for evaluating language agents in multi-step trip planning with constraints.
What's inside
Contains English text queries and tabular data. For each query, the agent must build a daily itinerary including transport, dining, attractions, and lodging. Totaling 1,225 queries, it is a benchmark for evaluating tool use and complex planning with strict constraints.
What you can do with it
- Evaluate LLM agents in tool use
- Test trip planners with constraints
- Compare multi-step planning strategies
- Tasks
- Text generation
- Languages
- English
- Size
- 1K–10K rows
- Downloads this month
- 3.6K
- Likes
- 89
How to load it
from datasets import load_dataset
ds = load_dataset("osunlp/TravelPlanner")