ResearchTasksMulti-agent systems coordinationMulti-agent systems coordinationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHotPotQA-MAS, HumanEval-MAS, ALFWorld-Multi, WebArena-Coord (mean)PSMAS-WPA65.2Token Cost8Apr 21, 2026
HotPotQA-MAS, HumanEval-MAS, ALFWorld-Multi, WebArena-Coord (mean)PSMAS-WPA65.2Token Cost8Apr 21, 2026