# Booking

Source: [Booking](<https://www.sota2.com/research/dataset/booking>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Benchmarks

Page 1 of 1. This is an index page, not the full collection.

- [Targeted Prompt Injection on ExpediaBooking](<https://www.sota2.com/research/sota/targeted-prompt-injection-on-expediabooking.md>): Targeted Prompt Injection; ExpediaBooking.

- [Privacy-preserving payload sanitization on 100 medical-booking workflows (test)](<https://www.sota2.com/research/sota/privacy-preserving-payload-sanitization-on-100-medical-booking-workflows-test.md>): Privacy-preserving payload sanitization; 100 medical-booking workflows (test).

- [Web Agent Navigation on BookingArena 1.0 (test)](<https://www.sota2.com/research/sota/web-agent-navigation-on-bookingarena-1-0-test.md>): Web Agent Navigation; BookingArena 1.0 (test).

- [Web GUI Task Automation on Booking offline-to-online transfer](<https://www.sota2.com/research/sota/web-gui-task-automation-on-booking-offline-to-online-transfer.md>): Web GUI Task Automation; Booking offline-to-online transfer.

- [Re-ranking on Airbnb booking dataset offline](<https://www.sota2.com/research/sota/re-ranking-on-airbnb-booking-dataset-offline.md>): Re-ranking; Airbnb booking dataset offline.

- [Decision Making on HotelBookings](<https://www.sota2.com/research/sota/decision-making-on-hotelbookings.md>): Decision Making; HotelBookings.

- [First-try Success on Booking domain (test)](<https://www.sota2.com/research/sota/first-try-success-on-booking-domain-test.md>): First-try Success; Booking domain (test).

- [Agentic Workflow Automation on Booking domain](<https://www.sota2.com/research/sota/agentic-workflow-automation-on-booking-domain.md>): Agentic Workflow Automation; Booking domain.

- [Tool Routing on Travel Booking Scenario T6: Triple Failure 1.0 (test)](<https://www.sota2.com/research/sota/tool-routing-on-travel-booking-scenario-t6-triple-failure-1-0-test.md>): Tool Routing; Travel Booking Scenario T6: Triple Failure 1.0 (test).

- [Tool Routing on Travel Booking Scenario T5: Hotel+Car Down 1.0 (test)](<https://www.sota2.com/research/sota/tool-routing-on-travel-booking-scenario-t5-hotel-plus-car-down-1-0-test.md>): Tool Routing; Travel Booking Scenario T5: Hotel+Car Down 1.0 (test).

- [Tool Routing on Travel Booking Scenario T4: Budget Risk 1.0 (test)](<https://www.sota2.com/research/sota/tool-routing-on-travel-booking-scenario-t4-budget-risk-1-0-test.md>): Tool Routing; Travel Booking Scenario T4: Budget Risk 1.0 (test).

- [Tool Routing on Travel Booking Scenario T3: Cascading 1.0 (test)](<https://www.sota2.com/research/sota/tool-routing-on-travel-booking-scenario-t3-cascading-1-0-test.md>): Tool Routing; Travel Booking Scenario T3: Cascading 1.0 (test).

- [Tool Routing on Travel Booking Scenario T2: Flight API Down 1.0 (test)](<https://www.sota2.com/research/sota/tool-routing-on-travel-booking-scenario-t2-flight-api-down-1-0-test.md>): Tool Routing; Travel Booking Scenario T2: Flight API Down 1.0 (test).

- [Tool Routing on Travel Booking Scenario T1: Happy Path 1.0 (test)](<https://www.sota2.com/research/sota/tool-routing-on-travel-booking-scenario-t1-happy-path-1-0-test.md>): Tool Routing; Travel Booking Scenario T1: Happy Path 1.0 (test).

- [Tool Routing on 19 Representative Scenario Flows (test)](<https://www.sota2.com/research/sota/tool-routing-on-19-representative-scenario-flows-test.md>): Tool Routing; 19 Representative Scenario Flows (Customer Support, Travel Booking, Content Moderation) (test).

- [Location Retrieval on Airbnb Offline Evaluation 7-day held-out bookings (test)](<https://www.sota2.com/research/sota/location-retrieval-on-airbnb-offline-evaluation-7-day-held-out-bookings-test.md>): Location Retrieval; Airbnb Offline Evaluation 7-day held-out bookings (test).