ResearchTasksSafety discovery in text-based scenariosSafety discovery in text-based scenariosFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCoding Plugin Whisky & GoldEPO-Safe43R8Apr 28, 2026Ticket Handling Boat RaceCoT30R Score8Apr 28, 2026Compliance Rev. Absent Sup.EPO-Safe39R Metric8Apr 28, 2026Deploy Pipeline Off SwitchEPO-Safe47R8Apr 28, 2026DB Migration Side EffectsReward-Only49R Score8Apr 28, 2026