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

arXiv: https://arxiv.org/abs/2604.14668 · HTML: https://mlsanity.com/paper/2604.14668/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 21 of 21)

- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows](https://mlsanity.com/paper/2505.19897/) (2025)
- [Creating General User Models from Computer Use](https://mlsanity.com/paper/2505.10831/) (2025)
- [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024)
- [CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation](https://mlsanity.com/paper/2501.16609/) (2025)
- [Direct-Manipulation Visualization of Deep Networks](https://mlsanity.com/paper/1708.03788/) (2017)
- [Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking](https://mlsanity.com/paper/2402.08030/) (2024)
- [Morae: Proactively Pausing UI Agents for User Choices](https://mlsanity.com/paper/2508.21456/) (2025)
- [InsightLens: Augmenting LLM-Powered Data Analysis with Interactive Insight Management and Navigation](https://mlsanity.com/paper/2404.01644/) (2024)
- [DECEPTICON: How Dark Patterns Manipulate Web Agents](https://mlsanity.com/paper/2512.22894/) (2025)
- [ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent](https://mlsanity.com/paper/2507.18165/) (2025)
- [InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions](https://mlsanity.com/paper/2503.04110/) (2025)
- [BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks](https://mlsanity.com/paper/2404.07387/) (2024)
- [PosterMate: Audience-driven Collaborative Persona Agents for Poster Design](https://mlsanity.com/paper/2507.18572/) (2025)
- [Embedding Atlas: Low-Friction, Interactive Embedding Visualization](https://mlsanity.com/paper/2505.06386/) (2025)
- [Just-In-Time Objectives: A General Approach for Specialized AI Interactions](https://mlsanity.com/paper/2510.14591/) (2025)
- [Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software](https://mlsanity.com/paper/2504.15549/) (2025)
- [SAM: A Modular Framework for Self-Adapting Web Menus](https://mlsanity.com/paper/1901.08289/) (2019)
- [Pluto: Authoring Semantically Aligned Text and Charts for Data-Driven Communication](https://mlsanity.com/paper/2502.07725/) (2025)
- [Narvis: Authoring Narrative Slideshows for Introducing Data Visualization Designs](https://mlsanity.com/paper/1907.05609/) (2019)
- [Comparative Evaluations of Visualization Onboarding Methods](https://mlsanity.com/paper/2203.15418/) (2022)

## 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.