Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Hugging Face Daily Papers Papers
gui-agents qwen ai-agent foundation-model mobile-use computer-use browser-use

Summary

Qwen-UI-Agent is a new foundation GUI agent from Alibaba's Qwen team that handles mobile, computer, web, and DeepSearch tasks with state-of-the-art performance on mobile-use benchmarks and competitive results on computer/browser tasks, combining GUI and CLI actions in a unified action space.

GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision agents that operate reliably on real devices, execute workflows across platforms, combine GUI interaction with CLI execution, complete long-horizon tasks, proactively initiate useful services, and autonomously improve their capabilities with minimal human effort. Guided by this vision, we present Qwen-UI-Agent, a real-world centric foundation GUI agent spanning mobile, computer-use, web, and DeepSearch environments. Qwen-UI-Agent combines diverse sandbox environments with a large-scale real-device mobile runtime. Its unified action space interleaves GUI operations with CLI execution and generates batched actions in a single model turn. An AutoResearch-style data flywheel uses agents to construct tasks and environments, diagnose failures, and plan subsequent iterations. Online RL supports training on trajectories exceeding 100 turns, with over 10,000 concurrent environments accelerating rollout. A lightweight harness layer supports proactive service initiation and stateful workflows across mobile and computer. Across a broad suite of evaluations, Qwen-UI-Agent sets state-of-the-art performance on mobile-use benchmarks while delivering competitive performance on computer- and browser-use tasks against frontier models, including Opus 4.8, Gemini 3.1 Pro, and GPT-5.6 Sol. On mobile use, it achieves 82.1% on MobileWorld, 92.2% on MobileWorld-Real, and 97.5% on AndroidDaily. On computer use, it achieves 79.5% on OSWorld-Verified and a 40.0% partial-progress score on OSWorld-v2. On browser use and GUI grounding, it achieves 73.6% on WebArena and 81.5% on ScreenSpot-Pro, respectively.
Original Article
View Cached Full Text

Cached at: 07/31/26, 05:52 AM

Paper page - Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Source: https://huggingface.co/papers/2607.28227 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

GUIagentshavethepotentialtobecomeageneralpurposeexecutoroverexistingdigitaldevices.Toadvancethemtowardreal-worlduse,weenvisionagentsthatoperatereliablyonrealdevices,executeworkflowsacrossplatforms,combineGUIinteractionwithCLIexecution,completelong-horizontasks,proactivelyinitiateusefulservices,andautonomouslyimprovetheircapabilitieswithminimalhumaneffort.Guidedbythisvision,wepresentQwen-UI-Agent,areal-worldcentricfoundationGUIagentspanningmobile,computer-use,web,andDeepSearchenvironments.Qwen-UI-Agentcombinesdiversesandboxenvironmentswithalarge-scalereal-devicemobileruntime.ItsunifiedactionspaceinterleavesGUIoperationswithCLIexecutionandgeneratesbatchedactionsinasinglemodelturn.AnAutoResearch-styledataflywheelusesagentstoconstructtasksandenvironments,diagnosefailures,andplansubsequentiterations.OnlineRLsupportstrainingontrajectoriesexceeding100turns,withover10,000concurrentenvironmentsacceleratingrollout.Alightweightharnesslayersupportsproactiveserviceinitiationandstatefulworkflowsacrossmobileandcomputer.Acrossabroadsuiteofevaluations,Qwen-UI-Agentsetsstate-of-the-artperformanceonmobile-usebenchmarkswhiledeliveringcompetitiveperformanceoncomputer-andbrowser-usetasksagainstfrontiermodels,includingOpus4.8,Gemini3.1Pro,andGPT-5.6Sol.Onmobileuse,itachieves82.1%onMobileWorld,92.2%onMobileWorld-Real,and97.5%onAndroidDaily.Oncomputeruse,itachieves79.5%onOSWorld-Verifiedanda40.0%partial-progressscoreonOSWorld-v2.OnbrowseruseandGUIgrounding,itachieves73.6%onWebArenaand81.5%onScreenSpot-Pro,respectively.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.28227

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/2607.28227 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.28227 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.28227 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Qwen3.7: The Agent Frontier (15 minute read)

TLDR AI

Alibaba's Qwen team has released Qwen3.7-Max, a proprietary agent-foundation model achieving top scores on multiple benchmarks including Terminal-Bench 2.0, SWE-Pro, and GPQA Diamond, with consistent performance across various code environments.

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

Papers with Code Trending

The MAI-UI technical report presents a family of foundation GUI agents in multiple sizes, addressing real-world deployment challenges with a self-evolving data pipeline, device-cloud collaboration, and online RL, achieving state-of-the-art results on GUI grounding and mobile navigation benchmarks.

Qwen/Qwen-AgentWorld-35B-A3B

Hugging Face Models Trending

Qwen releases Qwen-AgentWorld-35B-A3B, a native language world model that simulates agentic environments across seven domains via long chain-of-thought reasoning. The model is trained with a three-stage pipeline and supports MCP, Search, Terminal, SWE, Android, Web, and OS interactions.