mlsanityData to 7 Oct 2026

Beyond Chat and Clicks: GUI Agents for In-Situ Assistance via Live Interface Transformation

arXiv 2604.14668 ↗First posted 16 Apr 2026cs.HCcited by 0

On the map: LLM agents and tool use → GUI and mobile agents

Abstract (arXiv)

Complex visual interfaces are powerful yet have a steep learning curve, as users must navigate feature-rich visual interfaces while reasoning about domain-specific operations. Existing approaches either deliver assistance through a separate chat-based interaction, or require substantial application-specific engineering to build support natively into each interface. To address the gaps, we propose in-situ assistance: a mode of support delivered directly within any live web interface through lightweight, browser-level interventions on the Document Object Model (DOM), without rebuilding the application or modifying its underlying logic. We contribute a design space and a computational pipeline for DOM-mediated in-situ assistance, characterizing how GUI agents can insert, mutate, or recompose web elements to make the interface easier for users to understand, use, and navigate. We instantiate in-situ assistance in DOMSteer, a Chrome extension that interprets a user's help request and live interface context, grounds it to relevant UI elements, and executes reversible DOM manipulations directly on the live page to deliver assistance, including contextual tooltips, control highlighting, layout reorganization. Quantitative evaluations on two complex visual interfaces show that DOMSteer delivers reliable and efficient in-situ assistance. Use cases and a comparative user study with baseline ChatGPTAtlas demonstrate the usability and effectiveness of DOMSteer. Altogether, these findings point to a broader role for GUI agents: not just assisting from the sidelines, but actively reconfiguring live interfaces to support users in the moment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 62 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

21 of 62 references.

References · 21

  1. 2023Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfacescited by 71
  2. 2025ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflowscited by 47
  3. 2025Creating General User Models from Computer Usecited by 44
  4. 2025CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigationcited by 35
  5. 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 34
  6. 2017Direct-Manipulation Visualization of Deep Networkscited by 26
  7. 2024Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seekingcited by 24
  8. 2025Morae: Proactively Pausing UI Agents for User Choicescited by 18
  9. 2024InsightLens: Augmenting LLM-Powered Data Analysis with Interactive Insight Management and Navigationcited by 17
  10. 2025ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agentcited by 14
  11. 2025InterChat: Enhancing Generative Visual Analytics using Multimodal Interactionscited by 13
  12. 2025DECEPTICON: How Dark Patterns Manipulate Web Agentscited by 13
9 more
  1. 2024BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebookscited by 12
  2. 2025PosterMate: Audience-driven Collaborative Persona Agents for Poster Designcited by 9
  3. 2025Embedding Atlas: Low-Friction, Interactive Embedding Visualizationcited by 7
  4. 2025Just-In-Time Objectives: A General Approach for Specialized AI Interactionscited by 7
  5. 2025Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Softwarecited by 5
  6. 2019SAM: A Modular Framework for Self-Adapting Web Menuscited by 3
  7. 2025Pluto: Authoring Semantically Aligned Text and Charts for Data-Driven Communicationcited by 3
  8. 2019Narvis: Authoring Narrative Slideshows for Introducing Data Visualization Designscited by 2
  9. 2022Comparative Evaluations of Visualization Onboarding Methodscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI Agents
  2. 2025GUIrilla: A Scalable Framework for Automated Desktop UI Exploration
  3. 2024Ponder & Press: Advancing Visual GUI Agent towards General Computer Control
  4. 2026UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
  5. 2025TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments
  6. 2026DocOS: Towards Proactive Document-Guided Actions in GUI Agents
  7. 2025WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point
  8. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents