ResearchTasksTask-oriented InteractionTask-oriented InteractionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMeal Kit Recommendation Multi-turnIn-context80Pass Rate8Mar 4, 2026To Do List Multi-turnSemantic XPath100Pass Rate8Mar 4, 2026Travel Itinerary Multi-turnIn-context90Pass Rate8Mar 4, 2026