ResearchTasksReward Function SynthesisFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedYouTube Production current (online)Self-Evolving Recommendation System0.03YouTube Level Metric1Feb 26, 2026
YouTube Production current (online)Self-Evolving Recommendation System0.03YouTube Level Metric1Feb 26, 2026