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

Source: https://huggingface.co/papers/2604.11784

Abstract

ClawGUI presents an open-source framework that addresses key challenges in GUI agent development through unified reinforcement learning, standardized evaluation, and cross-platform deployment capabilities.

GUI agentsdrive 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 fromenvironment instabilityandclosed pipelines,evaluation protocolsdrift silently across works, and trained agents rarely reach real users on real devices. We present ClawGUI, an open-source framework addressing these three gaps within a single harness. 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. ClawGUI-Eval enforces a fully standardized evaluation pipeline across 6 benchmarks and 11+ models, achieving 95.8\% reproduction against official baselines. ClawGUI-Agent brings trained agents to Android, HarmonyOS, and iOS through 12+ chat platforms withhybrid CLI-GUI controland persistent personalized memory. Trained end to end within this pipeline, ClawGUI-2B achieves 17.1\%Success Rateon MobileWorld GUI-Only, outperforming the same-scale MAI-UI-2B baseline by 6.0\%.

View arXiv pageView PDFProject pageGitHub1.12kAdd to collection

Get this paper in your agent:

hf papers read 2604\.11784

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2604.11784 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2604.11784 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2604.11784 in a Space README.md to link it from this page.

Collections including this paper6

Browse 6 collections that include this paper