ResearchTasksWeb-based ReasoningWeb-based ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWebShopTeacher (LLaMA-13B)34.8Average Reasoning Length (tokens)18Mar 13, 2026WebShopSC-GRPO77.88Avg@8 Success Rate7Jun 18, 2026