cs.AIFeb 8, 2026

Do Multi-Agents Dream of Electric Screens? Achieving 100% on AndroidWorld Through Task Decomposition

Authors: Pierre-Louis Favreau, Jean-Pierre Lo, Clement Guiguet, Charles Simon-Meunier, Nicolas Dehandschoewercker, Allen G. Roush, Judah Goldfeder, Ravid Shwartz-Ziv

Organizations: minitap · Thoughtworks · Columbia University · New York University

Abstract

We present Minitap's mobile-use, a multi-agent system for Android UI control, and evaluate it on the 116 tasks of AndroidWorld, on Android emulators in Minitap's cloud device infrastructure, real Pixel 7 phones from our device farm and the stock emulator. On fresh, held-out task instances (three pre-registered seeds never used during development), the final system reaches a pass@3 of 100.0% (95% CI 96.8-100.0); pass^3 is 94.0% (95% CI 89.7-97.4) and the mean success rate 98.0% (95% CI 96.0-99.7). Minitap decomposes each task across five LLM agents (planning, subgoal tracking, state capture, decision, execution) and deterministic nodes, with mechanisms that read typed text back from the device, verify the goal on device evidence and detect repeated failures. A study of the initial system measures what each part contributes: removing only the decomposition changes success by -26.1 [-35.6, -16.7] points, the mechanisms together add +11.7 [+2.2, +21.1] points over a single agent, and the decision agent is the one role that needs a frontier model. We then improve reliability with general changes, a few of them triggered by the goal's wording. On MobileMiniWoB++, a second benchmark never used during development, the final system improves on the initial one by 7.1 points (McNemar p = 0.035; 95% CI -0.5 to +14.7). Minitap is open source: https://github.com/minitap-ai/mobile-use

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Coati: Host-Grounded Execution for Installable Mobile GUI Agents

    Nov 2, 2026Yudou Ying, Pu Shi, Hanlei Shi +1Mobile GUI AgentsLLM Agent Reliability

  2. MATE: Mobile Agent Trustworthy Execution for Safe and Efficient Mobile Control

    Nov 19, 2026Minsuk Jang, Hee-Seon Kim, Hui-Cheol Yu +1Computer-Use Agent SafetyRuntime Enforcement for AI Agents

  3. PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents

    May 28, 2026Yuxuan Liu, Xin Lai, Junyi Li +21Mobile GUI AutomationMobile Agent Benchmarks