ResearchDatasetsStealth task trajectoriesStealth task trajectoriesFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsHidden objective detectionStealth task trajectories (pooled across american_airlines, day_trip, extract_email, and send_link tasks)98Hidden Objective 1 Score3
Hidden objective detectionStealth task trajectories (pooled across american_airlines, day_trip, extract_email, and send_link tasks)98Hidden Objective 1 Score3