Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation

• URL: http://arxiv.org/abs/2504.16073v1
• Date: Tue, 22 Apr 2025 17:52:42 GMT
• Title: Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
• Authors: Zhiyuan Hu, Shiyun Xiong, Yifan Zhang, See-Kiong Ng, Anh Tuan Luu, Bo An, Shuicheng Yan, Bryan Hooi,
• Abstract summary: We propose an approach that guides VLM agents with process supervision by a reward model during GUI navigation and control at inference time.<n>This guidance allows the VLM agent to optimize actions at each inference step, thereby improving performance in both static and dynamic environments.
• Score: 101.09478572153239
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in visual language models (VLMs) have notably enhanced their capabilities in handling complex Graphical User Interface (GUI) interaction tasks. Despite these improvements, current frameworks often struggle to generate correct actions in challenging GUI environments. State-of-the-art commercial VLMs are black-boxes, and fine-tuning open-source VLMs for GUI tasks requires significant resources. Additionally, existing trajectory-level evaluation and refinement techniques frequently fall short due to delayed feedback and local optimization issues. To address these challenges, we propose an approach that guides VLM agents with process supervision by a reward model during GUI navigation and control at inference time. This guidance allows the VLM agent to optimize actions at each inference step, thereby improving performance in both static and dynamic environments. In particular, our method demonstrates significant performance gains in three GUI navigation tasks, achieving a 3.4% improvement in single step action accuracy for static environments, along with a around 33% increase in task success rate in one dynamic environment. With further integration of trajectory reflection and retry mechanisms, we also demonstrate even greater enhancement in task success.

Related papers

• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents [16.72683291432717]
  name is the first reinforcement learning framework designed to enhance the capabilities of LVLMs in high-level real-world task scenarios.<n>name achieves superior performance using only 0.02% of the data compared to previous state-of-the-art methods like OS-Atlas.
  arXiv  Detail & Related papers  (2025-04-14T17:45:54Z)
• Breaking the Data Barrier -- Building GUI Agents Through Task Generalization [25.129269032612832]
  We propose training Vision Language Models (VLMs) on data-rich, reasoning-intensive tasks during a dedicated mid-training stage. We explore a range of tasks with readily available instruction-tuning data, including GUI perception, multimodal reasoning, and textual reasoning. Our work provides valuable insights into cross-domain knowledge transfer for GUI agents and offers a practical approach to addressing data scarcity challenges.
  arXiv  Detail & Related papers  (2025-04-14T11:35:02Z)
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents [58.18100825673032]
  This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions.<n>In the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively)
  arXiv  Detail & Related papers  (2025-01-21T17:48:10Z)
• Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment [58.94611347128066]
  Task Preference Optimization (TPO) is a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks.<n>By leveraging rich visual labels during training, TPO significantly enhances the MLLM's multimodal capabilities and task-specific performance.<n>Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models.
  arXiv  Detail & Related papers  (2024-12-26T18:56:05Z)
• Improved GUI Grounding via Iterative Narrowing [0.03922370499388702]
  We introduce a visual prompting framework that employs an iterative narrowing mechanism to improve the performance of both general and fine-tuned models in GUI grounding. For evaluation, we tested our method on a comprehensive benchmark comprising various UI platforms and provided the code to reproduce our results.
  arXiv  Detail & Related papers  (2024-11-18T05:47:12Z)
• Dynamic Planning for LLM-based Graphical User Interface Automation [48.31532014795368]
  We propose a novel approach called Dynamic Planning of Thoughts (D-PoT) for LLM-based GUI agents.<n>D-PoT involves the dynamic adjustment of planning based on the environmental feedback and execution history.<n> Experimental results reveal that the proposed D-PoT significantly surpassed the strong GPT-4V baseline by +12.7%.
  arXiv  Detail & Related papers  (2024-10-01T07:49:24Z)
• GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding [73.9254861755974]
  This paper introduces a new dataset, termed GUI-World, which features meticulously crafted Human-MLLM annotations. We evaluate the capabilities of current state-of-the-art MLLMs, including Image LLMs and Video LLMs, in understanding various types of GUI content.
  arXiv  Detail & Related papers  (2024-06-16T06:56:53Z)
• Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning [79.38140606606126]
  We propose an algorithmic framework that fine-tunes vision-language models (VLMs) with reinforcement learning (RL) Our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning. We demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks.
  arXiv  Detail & Related papers  (2024-05-16T17:50:19Z)
• ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation [30.693616802332745]
  This paper presents a novel benchmark, AssistGUI, to evaluate whether models are capable of manipulating the mouse and keyboard on the Windows platform in response to user-requested tasks. We propose an advanced Actor-Critic framework, which incorporates a sophisticated GUI driven by an AI agent and adept at handling lengthy procedural tasks.
  arXiv  Detail & Related papers  (2023-12-20T15:28:38Z)

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.