Paper 2604.11784
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
- Published
- Apr 2026
- Research lab
- Independent
- Citations
- 10
- GitHub
- Not linked
01 In brief
Summary
ClawGUI is an open-source framework that integrates online reinforcement learning (RL) training, standardized evaluation, and real-device deployment for GUI agents.
It addresses three gaps: closed training pipelines, misaligned evaluation protocols, and a broken deployment loop.
ClawGUI-RL provides the first open-source RL infrastructure supporting parallel virtual environments and real physical devices, integrating GiGPO with a Process Reward Model for dense step-level supervision.
ClawGUI-Eval enforces a standardized three-stage pipeline (Infer, Judge, Metric) across 6 benchmarks and 11+ models, achieving a 95.8% reproduction rate against official baselines.
ClawGUI-Agent deploys trained agents to Android, HarmonyOS, and iOS via 12+ chat platforms, using hybrid CLI-GUI control and persistent personalized memory.
Trained end-to-end, ClawGUI-2B achieves 17.1% Success Rate on MobileWorld GUI-Only, outperforming the same-scale MAI-UI-2B baseline by 6.0% and larger models like Qwen3-VL-32B (11.9%) and UI-Venus-72B (16.4%).
Replacing GRPO with GiGPO yields a 2.6% improvement (14.5% to 17.1%), confirming the value of dense credit assignment.
The framework is validated end-to-end, with all code and predictions released publicly.
02 From the paper
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\%.