ResearchDatasetsPlancraftFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-agent system task solvingplancraft88.7Accuracy21World ModelingPlancraft98.4Smelt20Planning and self-evolution under curriculum settingPlanCraft72.5Success Rate (Easy)7Sequential PlanningPlanCraft39.1Performance Change vs. SAS1