ResearchDatasetsmanifest-defined shared-core domainsmanifest-defined shared-core domainsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLong-Horizon Evaluation with Simulator Feedback10 manifest-defined shared-core domains (de novo)29Success Rate (1-turn)7
Long-Horizon Evaluation with Simulator Feedback10 manifest-defined shared-core domains (de novo)29Success Rate (1-turn)7