ResearchTasksEnd-to-end task-oriented dialogueFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMultiWOZ (test)EWC+RL94Task Success Rate78Jun 9, 2026MultiWOZ 2.1 (test)DarwinTOD22.19BLEU ScoreEnd-to-End Task-Oriented Dialogue on MultiWOZ 2.1 (test) performance trend57Mar 11, 2026MultiWOZ 2.0 (test)LAVA97.5Inform Accuracy22Feb 26, 2026MultiWOZ 2.2 (test)FNCTOD-LLAMA2-13B0.379JGA8Feb 26, 2026
MultiWOZ 2.1 (test)DarwinTOD22.19BLEU ScoreEnd-to-End Task-Oriented Dialogue on MultiWOZ 2.1 (test) performance trend57Mar 11, 2026