New Mobilerun VA is now in beta — a hosted 24/7 agent for mobile automation
Methodology

Benchmark method.

The fundamental shift replaces sequential planning with dynamic feedback loops. The Manager creates high-level tasks, the Executor takes one concrete action, then the Manager immediately reassesses.

Architecture

The Manager–Executor loop.

A tight plan → execute → observe → reassess cycle, instead of plan-then-execute.

feedback loop
plan
Manager creates task
execute
Single action
observe
Read environment
reassess
Manager replans
Previous

Sequential planning

Plan all stepsExecute in orderNo adaptation
New

Dynamic feedback loop

01

Manager creates a high-level task

02

Executor takes one concrete action

03

System observes environment changes

04

Manager reassesses and replans

Improvements

Six technical improvements.

The innovations behind state-of-the-art performance on AndroidWorld.

01

Specialized Text Agent

Routes text-intensive tasks to a dedicated agent with Python shell access. Receives accessibility trees plus current text context and can atomically clear and replace content.

  • Routes when Manager tags items as text tasks
  • Receives accessibility trees and focused element context
  • Atomic clear/replace for reliable text editing
02

Contextual Awareness

Enhanced through device date injection, 0.5-second screen stabilization waits, disabled pointer visualization, differential state tracking, and automatic app capability extraction.

  • Device date injected into context
  • 0.5s screen stabilization before reads
  • Differential state: current vs. previous accessibility tree
  • Automatic app capability extraction
03

Transparent Communication

Executors output three components — thought process, chosen action, and description — all injected into Manager context for full decision rationale.

04

Memory System

Guidance scattered throughout system prompts with repeated context in multiple sections for consistent availability. Injections into both system prompt and final user message.

05

Expanded Actions

Eight action primitives covering the full interaction surface of mobile devices, from simple taps to complex clipboard operations.

06

Prompt Engineering

Iterative refinement across system prompts through strategic distribution rather than concentration of instructions. Model-specific optimization patterns.

Primitives

Eight action primitives.

Covering the full interaction surface of a mobile device.

01 click (by index)
02 long_press
03 type (with focus parameter)
04 system_button
05 swipe (coordinate-based)
06 open_app (by name)
07 copy (clipboard)
08 paste (with clear options)
Core insight

Tight feedback loops, task-specific routing, rich state observability, and dynamic replanning outperform rigid plan-then-execute models for mobile UI automation.

feedback loopstask routingstate observabilitydynamic replanning
Research

Peer-reviewed research.

The mobilerun agent architecture is studied in published academic work.

The Web Conference 2026 (WWW '26) arXiv:2601.19306

Curiosity Driven Knowledge Retrieval for Mobile Agents

Sijia Li, Xiaoyu Tan, Shahir Ali, Niels Schmidt, Gengchen Ma, Xihe Qiu

Co-authored by Droidrun's Shahir Ali and mobilerun co-founder Niels Schmidt and published at the ACM Web Conference 2026, the paper introduces uncertainty-driven retrieval of app knowledge — organized as AppCards, the concept behind the framework's App Instruction Cards — for mobile GUI agents. Evaluated on AndroidWorld using the open-source mobilerun (droidrun) framework for stable execution, curiosity-driven retrieval reaches an 88.8% success rate with GPT-5 — reported in the paper as a new state of the art over the prior published best of 84.5% — with consistent gains in task success and robustness across models and difficulty levels.

See the results.

The full benchmark — 91.4% success across 116 AndroidWorld tasks.