ResearchDatasetsShopTrajQAShopTrajQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTool-use ReasoningShopTrajQA 32k context62.6Accuracy14Tool-use ReasoningShopTrajQA 64k context60.1Accuracy13