ResearchDatasetsScienceWorld, τ-Bench, and PlanCraftScienceWorld, τ-Bench, and PlanCraftFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCross-benchmark aggregate rankingScienceWorld, τ-Bench, and PlanCraft1.6Aggregate Rank7