ResearchTasksOff-Policy Generative RecommendationOff-Policy Generative RecommendationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedIndustrial Recommender System Evolutionary Dynamics (converged state)DRPO1.96eCPM5Feb 26, 2026