GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

• URL: http://arxiv.org/abs/2512.02423v1
• Date: Tue, 02 Dec 2025 05:11:23 GMT
• Title: GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning
• Authors: Haolong Yan, Yeqing Shen, Xin Huang, Jia Wang, Kaijun Tan, Zhixuan Liang, Hongxin Li, Zheng Ge, Osamu Yoshie, Si Li, Xiangyu Zhang, Daxin Jiang,
• Abstract summary: Real-world PC software and mobile Apps are often complex and proprietary, making it difficult to obtain the comprehensive environment information needed for agent training and evaluation.<n>We introduce GUI Exploration Lab, a simulation environment engine for GUI agent navigation research.<n>Through extensive experiments, we find that supervised fine-tuning enables effective memorization of fundamental knowledge, serving as a crucial foundation for subsequent training.<n>We validate our methods on both static and interactive benchmarks, demonstrating that our findings generalize effectively to real-world scenarios.
• Score: 47.281652821908295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC software and mobile Apps, are often complex and proprietary, making it difficult to obtain the comprehensive environment information needed for agent training and evaluation. This limitation hinders systematic investigation and benchmarking of agent navigation capabilities. To address this limitation, we introduce GUI Exploration Lab, a simulation environment engine for GUI agent navigation research that enables flexible definition and composition of screens, icons, and navigation graphs, while providing full access to environment information for comprehensive agent training and evaluation. Through extensive experiments, we find that supervised fine-tuning enables effective memorization of fundamental knowledge, serving as a crucial foundation for subsequent training. Building on this, single-turn reinforcement learning further enhances generalization to unseen scenarios. Finally, multi-turn reinforcement learning encourages the development of exploration strategies through interactive trial and error, leading to further improvements in screen navigation performance. We validate our methods on both static and interactive benchmarks, demonstrating that our findings generalize effectively to real-world scenarios. These findings demonstrate the advantages of reinforcement learning approaches in GUI navigation and offer practical guidance for building more capable and generalizable GUI agents.

Related papers

• Mano Technical Report [29.551514304095296]
  Mano is a robust GUI agent built upon a multi-modal foundation model pre-trained on extensive web and computer system data.<n>Mano demonstrates state-of-the-art performance on multiple GUI benchmarks, including Mind2Web and OSWorld.
  arXiv  Detail & Related papers  (2025-09-22T03:13:58Z)
• MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning [83.81404871748438]
  MagicGUI is a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environments.<n>The framework is underpinned by six key components, including a comprehensive and accurate dataset, enhanced perception and grounding capabilities, a comprehensive and unified action space, and planning-oriented reasoning mechanisms.
  arXiv  Detail & Related papers  (2025-07-19T12:33:43Z)
• MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment [63.62778707277929]
  MobileGUI-RL is a scalable framework that trains GUI agent in online environment.<n>It synthesizes a curriculum of learnable tasks through self-exploration and filtering.<n>It adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards.
  arXiv  Detail & Related papers  (2025-07-08T07:07:53Z)
• Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents [15.303188467166752]
  We present CogniGUI, a cognitive framework developed to overcome limitations by enabling adaptive learning for GUI automation resembling human-like behavior.<n>To assess the generalization and adaptability of agent systems, we introduce ScreenSeek, a comprehensive benchmark that includes multi application navigation, dynamic state transitions, and cross interface coherence.<n> Experimental results demonstrate that CogniGUI surpasses state-of-the-art methods in both the current GUI grounding benchmarks and our newly proposed benchmark.
  arXiv  Detail & Related papers  (2025-06-22T06:30:52Z)
• ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World [11.401732438387704]
  Existing GUI agents based on vision-language models (VLMs) often fail to generalize to novel environments.<n>We introduce ScreenExplorer, a VLM trained via Group Relative Policy Optimization (GRPO) in real, dynamic, and open-ended GUI environments.<n>We also introduce a world-model-based curiosity reward function to help the agent overcome the cold-start phase of exploration.
  arXiv  Detail & Related papers  (2025-05-25T11:13:03Z)
• A Survey on (M)LLM-Based GUI Agents [62.57899977018417]
  Graphical User Interface (GUI) Agents have emerged as a transformative paradigm in human-computer interaction.<n>Recent advances in large language models and multimodal learning have revolutionized GUI automation across desktop, mobile, and web platforms.<n>This survey identifies key technical challenges, including accurate element localization, effective knowledge retrieval, long-horizon planning, and safety-aware execution control.
  arXiv  Detail & Related papers  (2025-03-27T17:58:31Z)
• GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration [22.814882629516635]
  We introduce GUI-Xplore, a dataset meticulously designed to enhance cross-application and cross-task generalization.<n>To fully exploit GUI-Xplore's unique features, we propose Xplore-Agent, a GUI agent framework that combines Action-aware GUI Modeling with Graph-Guided Environment Reasoning.
  arXiv  Detail & Related papers  (2025-03-22T09:30:37Z)
• GUI Agents: A Survey [159.7656453000263]
  Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction.<n>Motivated by the growing interest and fundamental importance of GUI agents, we provide a comprehensive survey that categorizes their benchmarks, evaluation metrics, architectures, and training methods.
  arXiv  Detail & Related papers  (2024-12-18T04:48:28Z)
• Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction [69.57190742976091]
  Aguvis is a vision-based framework for autonomous GUI agents.<n>It standardizes cross-platform interactions and incorporates structured reasoning via inner monologue.<n>It achieves state-of-the-art performance across offline and real-world online benchmarks.
  arXiv  Detail & Related papers  (2024-12-05T18:58:26Z)
• Large Language Model-Brained GUI Agents: A Survey [42.82362907348966]
  multimodal models have ushered in a new era of GUI automation.<n>They have demonstrated exceptional capabilities in natural language understanding, code generation, and visual processing.<n>These agents represent a paradigm shift, enabling users to perform intricate, multi-step tasks through simple conversational commands.
  arXiv  Detail & Related papers  (2024-11-27T12:13:39Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.