ResearchTasksContinual-memory deploymentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedALFWorldAuto-Dreamer60.21Success Rate11May 21, 2026ScienceWorldAuto-Dreamer41.07Success Rate11May 21, 2026WebArenaAuto-Dreamer52.3Macro-Averaged Success Rate9May 21, 2026