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

arXiv:2604.11784v1 Announce Type: cross
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 textbfClawGUI, an open-source framework addressing these three gaps within a single harness. textbfClawGUI-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. textbfClawGUI-Eval enforces a fully standardized evaluation pipeline across 6 benchmarks and 11+ models, achieving 95.8% reproduction against official baselines. textbfClawGUI-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, textbfClawGUI-2B achieves 17.1% Success Rate on MobileWorld GUI-Only, outperforming the same-scale MAI-UI-2B baseline by 6.0%.