mlsanityData to 7 Oct 2026

UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning

arXiv 2503.21620 ↗First posted 27 Mar 2025cs.AIcited by 166

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

The recent DeepSeek-R1 has showcased the emergence of reasoning capabilities in LLMs through reinforcement learning (RL) with rule-based rewards. Despite its success in language models, its application in multi-modal domains, particularly in graphic user interface (GUI) agent tasks, remains under-explored. To address this issue, we propose UI-R1, the first framework to explore how rule-based RL can enhance the reasoning capabilities of multimodal large language models (MLLMs) for GUI action prediction tasks. Specifically, UI-R1 introduces a novel rule-based action reward, enabling model optimization via policy-based algorithms such as Group Relative Policy Optimization (GRPO). For efficient training, we curate a small yet high-quality dataset of 136 challenging tasks, encompassing five common action types on mobile devices. Experimental results demonstrate that our proposed UI-R1-3B achieves significant improvements over the base model (i.e. Qwen2.5-VL-3B) on both in-domain (ID) and out-of-domain (OOD) tasks, with average accuracy gains of 22.1% on ScreenSpot, 6.0% on ScreenSpot-Pro, and 12.7% on ANDROIDCONTROL. Furthermore, UI-R1-3B delivers competitive performance compared to larger models (e.g., OS-Atlas-7B) trained via supervised fine-tuning (SFT) on 76K samples. We additionally develop an optimized version, UI-R1-E-3B, which significantly improves both grounding efficiency and accuracy. These results underscore the potential of rule-based reinforcement learning to advance GUI understanding and control, paving the way for future research in this domain. Code website: https://github.com/lll6gg/UI-R1.

Key facts. Cited by 166 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 36 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

27 of 36 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning20 Mar
  2. 2025VisualPRM: An Effective Process Reward Model for Multimodal Reasoning13 Mar
  3. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL10 Mar
  4. 2025VisRL: Intention-Driven Visual Perception via Reinforced Reasoning10 Mar
  5. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models9 Mar
  6. 2025R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model7 Mar
  7. 2025Visual-RFT: Visual Reinforcement Fine-Tuning3 Mar
  8. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction5 Dec

Other references · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2025s1: Simple test-time scalingcited by 1,311
  5. 2023CogAgent: A Visual Language Model for GUI Agentscited by 692
  6. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 584
  7. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 553
  8. 2023AppAgent: Multimodal Agents as Smartphone Userscited by 407
  9. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningcited by 381
  10. 2024Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agentscited by 373
  11. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 370
  12. 2023Android in the Wild: A Large-Scale Dataset for Android Device Controlcited by 314
7 more
  1. 2024Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perceptioncited by 283
  2. 2024OmniParser for Pure Vision Based GUI Agentcited by 193
  3. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 187
  4. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Modelscited by 154
  5. 2024AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agentscited by 110
  6. 2024AppAgent v2: Advanced Agent for Flexible Mobile Interactionscited by 67
  7. 2025Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Taskscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 65; 2026: 101.

166 papers.

Sort:

By area:

  1. 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agentscited by 240
  2. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  3. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  4. 2025InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasonerscited by 140
  5. 2025GTA1: GUI Test-time Scaling Agentcited by 102
  6. 2025UI-Venus Technical Report: Building High-performance UI Agents with RFTcited by 90
  7. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  8. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalizationcited by 82
  9. 2025Grounded Reinforcement Learning for Visual Reasoningcited by 80
  10. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoningcited by 67
  11. 2025GUI-G2: Gaussian Reward Modeling for GUI Groundingcited by 60
  12. 2025ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Datacited by 58
38 more
  1. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 50
  2. 2026Self-Distilled Agentic Reinforcement Learningcited by 49
  3. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  4. 2025MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agentscited by 43
  5. 2026UI-Venus-1.5 Technical Reportcited by 39
  6. 2025UFO2: The Desktop AgentOScited by 38
  7. 2026Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Taskscited by 37
  8. 2025UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learningcited by 32
  9. 2026Code2World: A GUI World Model via Renderable Code Generationcited by 26
  10. 2025GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Taskscited by 25
  11. 2025OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agentscited by 25
  12. 2025Phi-Ground Tech Report: Advancing Perception in GUI Groundingcited by 24
  13. 2026WebXSkill: Skill Learning for Autonomous Web Agentscited by 24
  14. 2025RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learningcited by 22
  15. 2025UItron: Foundational GUI Agent with Advanced Perception and Planningcited by 22
  16. 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Roboticscited by 21
  17. 2026MobileDreamer: Generative Sketch World Model for GUI Agentcited by 21
  18. 2025Test-Time Reinforcement Learning for GUI Grounding via Region Consistencycited by 20
  19. 2025Auto-scaling Continuous Memory for GUI Agentcited by 19
  20. 2026RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL Systemcited by 19
  21. 2026KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluationcited by 19
  22. 2025Grounding Computer Use Agents on Human Demonstrationscited by 16
  23. 2026GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Trainingcited by 16
  24. 2025VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agentscited by 15
  25. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 15
  26. 2025Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessmentcited by 14
  27. 2025Ferret-UI Lite: Lessons from Building Small On-Device GUI Agentscited by 14
  28. 2025ProBench: Benchmarking GUI Agents with Accurate Process Informationcited by 14
  29. 2026GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RLcited by 14
  30. 2026Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correctioncited by 14
  31. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 13
  32. 2026OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Executioncited by 13
  33. 2026ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agentscited by 13
  34. 2025ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Searchcited by 12
  35. 2025Learning GUI Grounding with Spatial Reasoning from Visual Feedbackcited by 12
  36. 2025SynthAgent: Adapting Web Agents with Synthetic Supervisioncited by 12
  37. 2025Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agentscited by 11
  38. 2025PAL-UI: Planning with Active Look-back for Vision-Based GUI Agentscited by 11

50 most cited of 166 All 166 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning
  2. 2025ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay
  3. 2025CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks
  4. 2025GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning
  5. 2025UIPro: Unleashing Superior Interaction Capability For GUI Agents
  6. 2026LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning
  7. 2026MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation
  8. 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents