ResearchTasksOpen-set assistanceOpen-set assistanceFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOvercooked Task Generalization (held-out)Open-Set Corrective Assistance85.96Coaching Score (LLM-as-Judge)4Mar 6, 2026Overcooked Defects (held-out)Open-Set Corrective Assistance77.8Coaching (LLM-as-judge)4Mar 6, 2026
Overcooked Task Generalization (held-out)Open-Set Corrective Assistance85.96Coaching Score (LLM-as-Judge)4Mar 6, 2026