GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

• URL: http://arxiv.org/abs/2603.26266v2
• Date: Tue, 31 Mar 2026 08:17:51 GMT
• Title: GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation
• Abstract summary: Guide is a training-free, plug-and-play framework that resolves GUI agent domain bias.<n>It autonomously acquires domain-specific expertise from web tutorial videos.<n>It consistently yields over 5% improvements without modifying any model parameters or architecture.
• Score: 27.67914789321192
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these agents exhibit significant domain bias - they lack familiarity with the specific operation workflows (planning) and UI element layouts (grounding) of particular applications, limiting their real-world task performance. In this paper, we present GUIDE (GUI Unbiasing via Instructional-Video Driven Expertise), a training-free, plug-and-play framework that resolves GUI agent domain bias by autonomously acquiring domain-specific expertise from web tutorial videos through a retrieval-augmented automated annotation pipeline. GUIDE introduces two key innovations. First, a subtitle-driven Video-RAG pipeline unlocks video semantics through subtitle analysis, performing progressive three-stage retrieval - domain classification, topic extraction, and relevance matching - to identify task-relevant tutorial videos. Second, a fully automated annotation pipeline built on an inverse dynamics paradigm feeds consecutive keyframes enhanced with UI element detection into VLMs, inferring the required planning and grounding knowledge that are injected into the agent's corresponding modules to address both manifestations of domain bias. Extensive experiments on OSWorld demonstrate GUIDE's generality as a plug-and-play component for both multi-agent systems and single-model agents. It consistently yields over 5% improvements and reduces execution steps - without modifying any model parameters or architecture - validating GUIDE as an architecture-agnostic enhancement to bridge GUI agent domain bias.

Related papers

• DocOS: Towards Proactive Document-Guided Actions in GUI Agents [54.27655693145045]
  textbfDocOS is a benchmark designed to assess document-guided problem solving in fully interactive environments.<n>Experiments reveal that agents struggle to reliably locate relevant information during proactive search and frequently fail to faithfully ground retrieved instructions into precise actions.
  arXiv  Detail & Related papers  (2026-05-18T08:36:04Z)
• AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark [32.66632642377623]
  AutoGUI-v2 is a benchmark designed to evaluate deep GUI functionality understanding and interaction outcome prediction.<n>We construct the benchmark using a novel VLM-human collaborative pipeline that parses screenshots into hierarchical functional regions.<n>AutoGUI-v2 rigorously tests agents on region and element-level semantics, grounding, and dynamic state prediction.
  arXiv  Detail & Related papers  (2026-04-27T13:06:27Z)
• Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors [0.0]
  On-screen learning behavior provides valuable insights into how students seek, use, and create information during learning.<n>Recent development of Vision Language Models (VLMs) offers new opportunities to automate the labor-intensive manual coding.<n>This study demonstrates the effectiveness of VLM-based Multi-agent System for video analysis and contributes a scalable framework for multimodal data analytics.
  arXiv  Detail & Related papers  (2026-04-04T08:01:02Z)
• AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent [21.148033135113927]
  We introduce an instruct-BLIP-based multimodal architecture that achieves superior performance in GUI automation.<n>We propose an adaptive feature renormalization-based (a token-level affine transformation) technique that effectively enriches low-resolution image embeddings.<n>We evaluate AFRAgent on Meta-GUI and AITW benchmarks, establishing a new state-of-the-art baseline for smartphone automation.
  arXiv  Detail & Related papers  (2025-11-30T11:32:54Z)
• Retrieval-augmented GUI Agents with Generative Guidelines [45.75975553907856]
  We propose RAG-GUI, a lightweight VLM that leverages web tutorials at inference time.<n>RAG-GUI is first warm-started via supervised finetuning (SFT) and further refined through self-guided rejection sampling finetuning (RSF)<n>It consistently outperforms baseline agents and surpasses other inference baselines by 2.6% to 13.3% across two model sizes.
  arXiv  Detail & Related papers  (2025-09-29T02:04:20Z)
• 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)
• 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)
• InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection [38.833925781308665]
  We introduce textitInfiGUIAgent, an MLLM-based GUI Agent trained with a two-stage supervised fine-tuning pipeline.<n> Stage 1 enhances fundamental skills such as GUI understanding and grounding, while Stage 2 integrates hierarchical reasoning and expectation-reflection reasoning skills.<n>textitInfiGUIAgent achieves competitive performance on several GUI benchmarks.
  arXiv  Detail & Related papers  (2025-01-08T15:45:21Z)
• Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining [67.87810796668981]
  Information-Sensitive Cropping (ISC) and Self-Refining Dual Learning (SRDL)<n>Iris achieves state-of-the-art performance across multiple benchmarks with only 850K GUI annotations.<n>These improvements translate to significant gains in both web and OS agent downstream tasks.
  arXiv  Detail & Related papers  (2024-12-13T18:40:10Z)
• AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials [53.376263056033046]
  Existing approaches rely on expensive human annotation, making them unsustainable at scale.<n>We propose AgentTrek, a scalable data synthesis pipeline that generates web agent trajectories by leveraging publicly available tutorials.<n>Our fully automated approach significantly reduces data collection costs, achieving a cost of just $0.55 per high-quality trajectory without human annotators.
  arXiv  Detail & Related papers  (2024-12-12T18:59:27Z)
• AU-vMAE: Knowledge-Guide Action Units Detection via Video Masked Autoencoder [38.04963261966939]
  We propose a video-level pre-training scheme for facial action units (FAU) detection. At the heart of our design is a pre-trained video feature extractor based on the video-masked autoencoder. Our approach demonstrates substantial enhancement in performance compared to the existing state-of-the-art methods used in BP4D and DISFA FAUs datasets.
  arXiv  Detail & Related papers  (2024-07-16T08:07:47Z)
• VISA: Reasoning Video Object Segmentation via Large Language Models [64.33167989521357]
  We introduce a new task, Reasoning Video Object (ReasonVOS) This task aims to generate a sequence of segmentation masks in response to implicit text queries that require complex reasoning abilities. We introduce VISA (Video-based large language Instructed Assistant) to tackle ReasonVOS.
  arXiv  Detail & Related papers  (2024-07-16T02:29:29Z)

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.