EmbeWebAgent: Embedding Web Agents into Any Customized UI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |