RL for GUI Agents

RL: Reinforcement Learning · GUI: Graphical User Interface

Overview

These agents translate natural-language goals into grounded clicks, typing, navigation, and tool use while adapting to changing screens and long workflows. Most systems begin with supervised demonstrations, then optimize policies using PPO- or GRPO-style online learning, offline trajectory data, or hybrid training; rewards range from task-completion checks to step-level critics, environment-state verification, and spatial feedback. To reduce costly interaction, researchers use synthetic or mocked apps, trajectory reuse, world models, scalable sandboxes, and curricula, with evaluation on suites such as AndroidWorld, OSWorld, and ScreenSpot. Key challenges include trustworthy rewards under partial observability, efficient exploration and credit assignment for sparse long-horizon tasks, and reliable transfer to unseen apps, users, and real devices.

Latest papers

CardsList

58 papers9 papers in the last four weeks, down 31% on the four weeks before. 0.1% of all new papers.

  1. BiGrounder: Bidirectional Training Unlocks the Potential of GUI Grounding

    Nov 5, 2026Dengyao Shi, Tianyu Fu, Fei Hu +6GUI GroundingRL for GUI Agents

  2. NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale

    Nov 1, 2026Chaoyun Zhang, Bingxuan Li, Pinxue Guo +27Computer-Use AgentsLLM Agent Training

  3. Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps

    Oct 29, 2026Peitong Duan, Khashayar Gatmiry, Jeffrey Nichols +2RL for GUI AgentsDense Reward RL

  4. Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents

    Oct 29, 2026Yuxiang Chai, Quyu Kong, Panrong Tong +2RL for GUI AgentsReinforcement Learning

  5. Trace2World: Reconstructing App Worlds from Real Interaction Traces for Scalable GUI Agent Training

    Oct 22, 2026Zezhou Wang, Hanzhang Zhou, Panrong Tong +5RL for GUI AgentsWorld Model Evaluation

  6. VeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards

    Oct 19, 2026Zhizhou Wang, Yaxi Lu, Zhong Zhang +4AI Agent ReliabilityRL for GUI Agents

  7. Adaptation of Computer Use Agents to New Software with User Manuals

    Oct 16, 2026Chulhoon Yoon, Kyungri Park, Jinyeong Yun +3Computer-Use AgentsLLM Agent Training

  8. OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents

    Oct 15, 2026Bowen Yang, Kaiming Jin, Zichen Ding +8Computer-Use AgentsGUI Automation

  9. Player-1: Learning to Play from Synthetic Experience

    Oct 14, 2026Mingyu Ouyang, Yiran Wang, Siyuan Hu +9Game-Playing AgentsRL for Game AI

  10. ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation

    Oct 14, 2026Tengda Guo, Jiawang Hu, Yifei Tao +4Long-Horizon Agent TasksMemory-Augmented Agents

  11. GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning

    Oct 13, 2026Qingsong Xie, Jiahao Tian, Jiacheng Tang +5GUI GroundingMultimodal Grounding

  12. Adaptive-Group Process Rewards for GUI Agents

    Oct 13, 2026Zirui Shang, Yang Liu, Xin Shu +3RL for GUI AgentsProcess Reward Models

  13. Learn from Move: the Next Step for GUI Agents

    Oct 12, 2026Jiahao Lu, Yize Shen, Chuanyuan Tan +6GUI Agent BenchmarksGUI Agents

  14. OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools

    Oct 9, 2026Chenyang Yan, Yingying Zhang, Kanzhi Cheng +21Mobile Agent BenchmarksMobile GUI Agents

  15. When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction

    Oct 8, 2026Xiaolong Li, Xiaohan Xu, Jinyang Li +5Human-AI InteractionLLM Agent Harnesses

  16. SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents

    Sep 29, 2026Shengtian Yang, Ziyu Xiong, Kaibing Yang +6Reinforcement LearningRL for GUI Agents

  17. UI-Venus-2 Technical Report

    Aug 27, 2026Venus Team, Zhuohan Cai, Haoxing Chen +28GUI AgentsMultimodal Agents

  18. WM-R1: Training GUI Agents to Reason and leverage World Models with Reinforcement Learning

    Aug 27, 2026Yu Han, Tianwen QianRL for GUI AgentsModel-Based RL

  19. Task-Adaptive Rubrics for GUI Reward Modeling

    Aug 25, 2026Tao Xiong, Xavier Hu, Wenkai Wang +6Reward ModelingRubric-Based Evaluation

  20. GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis

    Aug 24, 2026Long Zhang, Yuhan Chen, Chaoran Zhang +7RL for GUI AgentsReward Design for RL

  21. Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents

    Aug 22, 2026Chengyang Gu, Le Zhang, Jingbo Zhou +6RL for GUI AgentsContrastive RL