mlsanityData to 14 Oct 2026

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment

arXiv 2507.05720 ↗First posted 8 Jul 2025cs.LG cs.CLcited by 52

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Recently, there has been a surge of vision-based GUI agents designed to automate everyday mobile and web tasks. These agents interpret raw GUI screenshots and autonomously decide where to click, scroll, or type, which bypasses handcrafted rules and app-specific APIs. However, most existing methods trained GUI agent in the offline environment using pre-collected trajectories. This approach limits scalability, causes overfitting to specific UI templates, and leads to brittle policies when faced with unseen environment. We present MobileGUI-RL, a scalable framework that trains GUI agent in online environment. MobileGUI-RL contains two key components. It (i) synthesizes a curriculum of learnable tasks through self-exploration and filtering, and (ii) adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards that balance task success and execution efficiency. Experiments on three online mobile-agent benchmarks show consistent gains, validating the effectiveness of our approach.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 31 of its 35 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

31 of 35 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents21 May
  2. 2025InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners19 Apr
  3. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction5 Dec
  4. 2024Android in the Zoo: Chain-of-Action-Thought for GUI Agents5 Mar

Other references · 27

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  7. 2023CogAgent: A Visual Language Model for GUI Agentscited by 704
  8. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 610
  9. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 563
  10. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 497
  11. 2024AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agentscited by 468
  12. 2024Understanding the planning of LLM agents: A surveycited by 421
15 more
  1. 2024Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agentscited by 382
  2. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 378
  3. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 353
  4. 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agentscited by 244
  5. 2024DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learningcited by 214
  6. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learningcited by 165
  7. 2024OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesiscited by 163
  8. 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
  9. 2024GUI Agents with Foundation Models: A Comprehensive Surveycited by 111
  10. 2025ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replaycited by 77
  11. 2024DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agentscited by 68
  12. 2025WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Modelcited by 61
  13. 2025ZeroGUI: Automating Online GUI Learning at Zero Human Costcited by 44
  14. 2025WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollbackcited by 17
  15. 2025WebRollback: Enhancing Web Agents with Explicit Rollback Mechanismscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 17; 2026: 35.

52 papers.

Sort:

By area:

  1. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 228
  2. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 215
  3. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  4. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  5. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  6. 2025Parallel-R1: Towards Parallel Thinking via Reinforcement Learningcited by 61
  7. 2025UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learningcited by 32
  8. 2026Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learningcited by 31
  9. 2026Code2World: A GUI World Model via Renderable Code Generationcited by 29
  10. 2025GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Taskscited by 26
  11. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  12. 2026MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Datacited by 21
38 more
  1. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  2. 2025Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversightcited by 16
  3. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 16
  4. 2026ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agentscited by 14
  5. 2025Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systemscited by 12
  6. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberationcited by 11
  7. 2026UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experiencecited by 11
  8. 2025Reinforcement Learning for Large Model: A Surveycited by 9
  9. 2026RelayLLM: Efficient Reasoning via Collaborative Decodingcited by 8
  10. 2026Scaling Coding Agents via Atomic Skillscited by 8
  11. 2026How Mobile World Model Guides GUI Agents?cited by 8
  12. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  13. 2026MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimizationcited by 7
  14. 2026SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RLcited by 7
  15. 2026Generalization in Online Reinforcement Learning for Mobile Agentscited by 6
  16. 2026Xiaomi-GUI-0 Technical Reportcited by 5
  17. 2026What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving Statescited by 5
  18. 2026Scaling GUI Agents with Visual State Transitionscited by 4
  19. 2026SlowBA: An efficiency backdoor attack towards VLM-based GUI agentscited by 3
  20. 2026GUI Agents with Reinforcement Learning: Toward Digital Inhabitantscited by 3
  21. 2025RISK: A Framework for GUI Agents in E-commerce Risk Managementcited by 2
  22. 2026Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decompositioncited by 2
  23. 2026StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agentscited by 2
  24. 2026AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agentscited by 2
  25. 2025Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automationcited by 1
  26. 2025UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoningcited by 1
  27. 2026Rethinking Agentic Reinforcement Learning In Large Language Modelscited by 1
  28. 2026PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Controlcited by 1
  29. 2026PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agentscited by 1
  30. 2026Software Engineering for and with GUI Agentcited by 1
  31. 2026Best-of-Q: Improving VLM agents with Q-function Action Ranking at Inferencecited by 0
  32. 2026OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agentscited by 0
  33. 2026Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignmentcited by 0
  34. 2026GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agentscited by 0
  35. 2026ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learningcited by 0
  36. 2026GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshotscited by 0
  37. 2026WM-R1: Training GUI Agents to Reason and leverage World Models with Reinforcement Learningcited by 0
  38. 2026Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agentscited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents
  2. 2025MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning
  3. 2025LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
  4. 2026GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis
  5. 2026MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration
  6. 2026UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents
  7. 2026UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents
  8. 2025GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning