ResearchTasksAgent RoutingAgent RoutingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAppWorld 14-agent poolπ_oracle93.3Score5Jun 15, 2026AgentDNS runtimeAgentGate94.25Action4Apr 10, 2026