# ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents

Source: [ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents](<https://www.sota2.com/research/paper/69ddca847d0172140ec7a037>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-18T06:00:01.392Z

Authors: Fei Tang, Zhiqiong Lu, Boxuan Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

Published: 2026-04-13T17:52:04.000Z

## Abstract

GUI agents drive applications through their visual interfaces instead of programmatic APIs, interacting with arbitrary software via taps, swipes, and keystrokes, reaching a long tail of applications that CLI-based agents cannot. Yet progress in this area is bottlenecked less by modeling capacity than by the absence of a coherent full-stack infrastructure: online RL training suffers from environment instability and closed pipelines, evaluation protocols drift silently across works, and trained agents rarely reach real users on real devices. We present \\textbf{ClawGUI}, an open-source framework addressing these three gaps within a single harness. \\textbf{ClawGUI-RL} provides the first open-source GUI agent RL infrastructure with validated support for both parallel virtual environments and real physical devices, integrating GiGPO with a Process Reward Model for dense step-level supervision. \\textbf{ClawGUI-Eval} enforces a fully standardized evaluation pipeline across 6 benchmarks and 11+ models, achieving 95.8\\% reproduction against official baselines. \\textbf{ClawGUI-Agent} brings trained agents to Android, HarmonyOS, and iOS through 12+ chat platforms with hybrid CLI-GUI control and persistent personalized memory. Trained end to end within this pipeline, \\textbf{ClawGUI-2B} achieves 17.1\\% Success Rate on MobileWorld GUI-Only, outperforming the same-scale MAI-UI-2B baseline by 6.0\\%.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [GUI Agent Interaction on MobileWorld GUI-Only](<https://www.sota2.com/research/sota/gui-agent-interaction-on-mobileworld-gui-only.md>): GUI Agent Interaction; MobileWorld GUI-Only; SR: 17.1.

- [Mobile GUI Navigation on MobileWorld GUI-Only 117 tasks (test)](<https://www.sota2.com/research/sota/mobile-gui-navigation-on-mobileworld-gui-only-117-tasks-test.md>): Mobile GUI Navigation; MobileWorld GUI-Only 117 tasks (test); Pass@1 Success Rate: 17.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.11784>)

[PDF](<https://arxiv.org/pdf/2604.11784.pdf>)

[Implementation](<https://github.com/ZJU-REAL/ClawGUI>)