ResearchTasksLLM behavior monitoringFor AI assistantsMarkdownContent indexLLM behavior monitoringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSHADE-Arena (test)Agent-ToM (external memory, Stage 1–2)75.2Accuracy8May 26, 2026