ResearchBenchmarksMobile App Task Automation on ESO Single-App Task Instructions Challenging Task Set Medium 1.0 (test)Mobile App Task Automation on ESO Single-App Task Instructions Challenging Task Set Medium 1.0 (test)Follow27.4Completion Rate (CR)See-Control26.0326.71527.428.085Dec 9, 2025Evaluation resultsMethodMethodLinksCompletion Rate (CR)Success Rate (SR)Success Error (SE)See-Control2025.1227.4—84