EmbeWebAgent: Embedding Web Agents into Any Customized UI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Chenyang, Fare, Clyde, Wilson, Matthew, Braines, Dave
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911450680786944
author Ma, Chenyang
Fare, Clyde
Wilson, Matthew
Braines, Dave
author_facet Ma, Chenyang
Fare, Clyde
Wilson, Matthew
Braines, Dave
contents Most web agents operate at the human interface level, observing screenshots or raw DOM trees without application-level access, which limits robustness and action expressiveness. In enterprise settings, however, explicit control of both the frontend and backend is available. We present EmbeWebAgent, a framework for embedding agents directly into existing UIs using lightweight frontend hooks (curated ARIA and URL-based observations, and a per-page function registry exposed via a WebSocket) and a reusable backend workflow that performs reasoning and takes actions. EmbeWebAgent is stack-agnostic (e.g., React or Angular), supports mixed-granularity actions ranging from GUI primitives to higher-level composites, and orchestrates navigation, manipulation, and domain-specific analytics via MCP tools. Our demo shows minimal retrofitting effort and robust multi-step behaviors grounded in a live UI setting. Live Demo: https://youtu.be/Cy06Ljee1JQ
format Preprint
id arxiv_https___arxiv_org_abs_2602_14865
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EmbeWebAgent: Embedding Web Agents into Any Customized UI
Ma, Chenyang
Fare, Clyde
Wilson, Matthew
Braines, Dave
Artificial Intelligence
Software Engineering
Most web agents operate at the human interface level, observing screenshots or raw DOM trees without application-level access, which limits robustness and action expressiveness. In enterprise settings, however, explicit control of both the frontend and backend is available. We present EmbeWebAgent, a framework for embedding agents directly into existing UIs using lightweight frontend hooks (curated ARIA and URL-based observations, and a per-page function registry exposed via a WebSocket) and a reusable backend workflow that performs reasoning and takes actions. EmbeWebAgent is stack-agnostic (e.g., React or Angular), supports mixed-granularity actions ranging from GUI primitives to higher-level composites, and orchestrates navigation, manipulation, and domain-specific analytics via MCP tools. Our demo shows minimal retrofitting effort and robust multi-step behaviors grounded in a live UI setting. Live Demo: https://youtu.be/Cy06Ljee1JQ
title EmbeWebAgent: Embedding Web Agents into Any Customized UI
topic Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2602.14865