ResearchTasksMulti-turn RL Task CompletionMulti-turn RL Task CompletionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedFrozenLakeQwen2.5-0.5B (TSR Beam Search)30Success Rate6Feb 26, 2026SokobanQwen2.5-0.5B (TSR Beam Search)38.3Success Rate6Feb 26, 2026