mlsanityData to 14 Oct 2026

Mobile-Agent-v3: Fundamental Agents for GUI Automation

arXiv 2508.15144 ↗First posted 21 Aug 2025cs.AIcited by 190

On the map: LLM agents and tool use → GUI and mobile agents

Abstract (arXiv)

This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question answering, planning, decision-making, and procedural knowledge. GUI-Owl-7B achieves 66.4 on AndroidWorld and 29.4 on OSWorld. Building on this, we propose Mobile-Agent-v3, a general-purpose GUI agent framework that further improves performance to 73.3 on AndroidWorld and 37.7 on OSWorld, setting a new state-of-the-art for open-source GUI agent frameworks. GUI-Owl incorporates three key innovations: (1) Large-scale Environment Infrastructure: a cloud-based virtual environment spanning Android, Ubuntu, macOS, and Windows, enabling our Self-Evolving GUI Trajectory Production framework. This generates high-quality interaction data via automated query generation and correctness validation, leveraging GUI-Owl to refine trajectories iteratively, forming a self-improving loop. It supports diverse data pipelines and reduces manual annotation. (2) Diverse Foundational Agent Capabilities: by integrating UI grounding, planning, action semantics, and reasoning patterns, GUI-Owl supports end-to-end decision-making and can act as a modular component in multi-agent systems. (3) Scalable Environment RL: we develop a scalable reinforcement learning framework with fully asynchronous training for real-world alignment. We also introduce Trajectory-aware Relative Policy Optimization (TRPO) for online RL, achieving 34.9 on OSWorld. GUI-Owl and Mobile-Agent-v3 are open-sourced at https://github.com/X-PLUG/MobileAgent.

Key facts. Cited by 190 papers in the map (data through 14 Oct 2026). Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use. Builds on 44 of its 54 references that are in the map. First posted on arXiv 21 Aug 2025.

Builds on

44 of 54 references.

Closest ancestors · 26

Same direction, newest first

  1. 2025OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use6 Aug
  2. 2025AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning2 Jun
  3. 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents21 May
  4. 2025Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis19 May
  5. 2025Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning18 May
  6. 2025InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners19 Apr
  7. 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents14 Apr
  8. 2025Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents1 Apr
  9. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agents21 Jan
  10. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks20 Jan
  11. 2024OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis27 Dec
  12. 2024GUI Agents: A Survey18 Dec
14 more
  1. 2024Large Language Model-Brained GUI Agents: A Survey27 Nov
  2. 2024GUI Agents with Foundation Models: A Comprehensive Survey7 Nov
  3. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agents30 Oct
  4. 2024AutoGLM: Autonomous Foundation Agents for GUIs28 Oct
  5. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Human10 Oct
  6. 2024Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents7 Oct
  7. 2024AppAgent v2: Advanced Agent for Flexible Mobile Interactions5 Aug
  8. 2024MobileFlow: A Multimodal LLM For Mobile GUI Agent5 Jul
  9. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration3 Jun
  10. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments11 Apr
  11. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvement12 Feb
  12. 2024ScreenAgent: A Vision Language Model-driven Computer Control Agent9 Feb
  13. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents17 Jan
  14. 2023AppAgent: Multimodal Agents as Smartphone Users21 Dec

Other references · 18

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  7. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 563
  8. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactioncited by 278
  9. 2024ShowUI: One Vision-Language-Action Model for GUI Visual Agentcited by 232
  10. 2024UFO: A UI-Focused Agent for Windows OS Interactioncited by 148
  11. 2024Cradle: Empowering Foundation Agents Towards General Computer Controlcited by 117
  12. 2025GTA1: GUI Test-time Scaling Agentcited by 106
6 more
  1. 2025UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interactioncited by 77
  2. 2025GUI-G2: Gaussian Reward Modeling for GUI Groundingcited by 63
  3. 2024Large Language Models Can Self-Improve At Web Agent Taskscited by 55
  4. 2025CoAct-1: Computer-using Multi-Agent System with Coding Actionscited by 35
  5. 2025OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Modelscited by 23
  6. 2024Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platformscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 44; 2026: 146.

190 papers.

Sort:

By area:

  1. 2025Qwen3-VL Technical Reportcited by 2,793
  2. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  3. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalizationcited by 94
  4. 2025MAI-UI Technical Report: Real-World Centric Foundation GUI Agentscited by 91
  5. 2026Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agentscited by 79
  6. 2025Latent Collaboration in Multi-Agent Systemscited by 73
  7. 2025MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environmentscited by 72
  8. 2025ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Datacited by 60
  9. 2026Self-Distilled Agentic Reinforcement Learningcited by 55
  10. 2026EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experiencecited by 53
  11. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  12. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
38 more
  1. 2026UI-Venus-1.5 Technical Reportcited by 41
  2. 2025Step-GUI Technical Reportcited by 39
  3. 2025UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learningcited by 32
  4. 2025OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agentscited by 29
  5. 2026Code2World: A GUI World Model via Renderable Code Generationcited by 29
  6. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
  7. 2025Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curationcited by 26
  8. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  9. 2026MobileDreamer: Generative Sketch World Model for GUI Agentcited by 23
  10. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  11. 2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
  12. 2026KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluationcited by 21
  13. 2025CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agentcited by 18
  14. 2025MGA: Memory-Driven GUI Agent for Observation-Centric Interactioncited by 18
  15. 2025MobileWorldBench: Towards Semantic World Modeling For Mobile Agentscited by 18
  16. 2026GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Trainingcited by 18
  17. 2026CaMeLs Can Use Computers Too: System-level Security for Computer Use Agentscited by 17
  18. 2025Ferret-UI Lite: Lessons from Building Small On-Device GUI Agentscited by 16
  19. 2026PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Recordscited by 16
  20. 2025VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agentscited by 15
  21. 2025WAREX: Web Agent Reliability Evaluation on Existing Benchmarkscited by 15
  22. 2025Environment Scaling for Interactive Agentic Experience Collection: A Surveycited by 13
  23. 2026OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Executioncited by 13
  24. 2026Generative Visual Code Mobile World Modelscited by 13
  25. 2025STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimizationcited by 12
  26. 2026UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agentscited by 12
  27. 2026Adaptive Milestone Reward for GUI Agentscited by 12
  28. 2025MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agentscited by 11
  29. 2025ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaborationcited by 11
  30. 2025AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Managementcited by 11
  31. 2026Behavior Knowledge Merge in Reinforced Agentic Modelscited by 11
  32. 2026UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experiencecited by 11
  33. 2026ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agentscited by 11
  34. 2025OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraftcited by 10
  35. 2025ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Taskscited by 10
  36. 2026PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarioscited by 10
  37. 2026OS-Themis: A Scalable Critic Framework for Generalist GUI Rewardscited by 10
  38. 2026AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applicationscited by 10

50 most cited of 190 All 190 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Mobile GUI Agents under Real-world Threats: Are We There Yet?
  2. 2026GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments
  3. 2025TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
  4. 2025A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation
  5. 2025MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
  6. 2025Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
  7. 2026MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization
  8. 2026ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents