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

TL;DR

ClawGUI is an open-source framework that unifies training, evaluation, and deployment of GUI agents across virtual and real devices, improving reproducibility and real-world applicability.

Contribution

It introduces a comprehensive full-stack infrastructure for GUI agents, including RL training, standardized evaluation, and deployment on multiple platforms.

Findings

Achieves 95.8% reproduction accuracy across benchmarks.

ClawGUI-2B outperforms baseline with 17.1% success rate on MobileWorld.

Supports deployment on Android, HarmonyOS, and iOS with multi-platform compatibility.

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\%.