TasksDueOnDate AndroidWorld, 2026-11-09. Agent: Lusor, model: DeepSeek V4.1 Flash (low). GOAL What tasks do I have due Friday in Tasks app? Answer with the titles only. If there are multiples titles, format your answer in a comma separated list. RESULT - Mobilerun's grader: pass - Google's grader: pass - Lusor time: 171.3 s; Mobilerun published time: 139.4 s (1.2x slower) - Lusor model cost: $0.0577; Mobilerun estimated cost: ~$0.23 - Lusor tool calls: 33; Mobilerun published actions: 3 - App skills: read tasks; has rules for this task: tasks FINAL ANSWER Follow up on support tickets, Review quarterly goals, Plan team outing STEPS (33; seconds into the video) 1. 28.54-28.54 s read ok Read tasks skill, then observe screen 2. 29.31-29.32 s get_ui_state ok Observe current screen 3. 30.10-33.60 s launch ok Launch Tasks app and observe list 4. 35.83-50.37 s map_app ok Map the full task list titles/due labels 5. 53.78-103.17 s map_app ok Open the three incomplete Fri-badged tasks and read their full due dates 6. 108.89-124.90 s scroll_to ok Scroll to 'Follow up on support tickets' row and open it to check its due date in the picker 7. 126.59-130.51 s swipe ok Scroll down the task list to reach the Fri-badged rows 8. 132.97-134.12 s tap_element ok Open 'Follow up on support tickets' and inspect its due date picker 9. 135.67-137.30 s tap_element ok Tap the 'Friday' due date field to open the date picker and read the selected day 10. 140.59-141.31 s tap_element ok Cancel picker, back to list, open 'Review quarterly goals' and check its due date 11. 142.64-143.20 s key ok Back to list, then open 'Review quarterly goals' 12. 144.79-145.71 s tap_element ok Open 'Review quarterly goals' detail and check its due date picker 13. 147.28-147.62 s key ok Discard accidental blank new-task editor and return to list 14. 149.30-149.59 s key ok Exit blank new-task editor back to the list 15. 151.26-152.14 s tap ok Open 'Review quarterly goals' detail away from FAB and check due date 16. 153.03-154.52 s tap_element ok Tap 'Friday' due field of Review quarterly goals and read selected day, then cancel 17. 155.58-156.01 s tap_element ok Cancel picker, back to list, scroll and open 'Plan team outing' 18. 156.92-157.32 s key ok Back on list; scroll down slightly and open 'Plan team outing' 19. 158.49-160.60 s swipe ok Scroll list slightly to reveal 'Plan team outing' row 20. 161.71-162.40 s tap ok Open 'Plan team outing' detail to verify due date 21. 163.32-165.00 s tap_element ok Tap 'Friday' due field of Plan team outing and read selected day 22. 169.65-170.12 s tap_element ok Cancel picker, back to list, check 'Reply to Emails' due date 23. 170.94-171.33 s key ok Back to list, scroll to 'Reply to Emails' and open to verify its due date 24. 172.40-173.12 s tap ok Open 'Reply to Emails' detail and verify its due date 25. 174.77-176.41 s tap_element ok Tap 'Friday 19:50' due field of Reply to Emails and read selected day 26. 179.07-179.59 s tap_element ok Cancel picker, back to list, check 'Read The Martian' due date 27. 180.71-181.02 s key ok Back to list, scroll down and open 'Read The Martian' to check due date 28. 182.52-184.88 s swipe ok Scroll to bottom of list to reach 'Read The Martian' row 29. 186.51-187.21 s tap ok Open 'Read The Martian' detail and check due date 30. 188.30-189.80 s tap_element ok Tap 'Friday 09:27' due field of Read The Martian and read selected day 31. 193.27-193.64 s tap_element ok Cancel picker, back out to list, re-read final screen, then answer 32. 194.90-195.20 s key ok Back to the task list and confirm the Friday rows one last time 33. 197.85-197.86 s done ok Answer delivered FILES - Video: video.mp4 (H.264), video.webm (VP9); poster: poster.webp - Data: task.json, steps.json