English

EmbeWebAgent: Embedding Web Agents into Any Customized UI

Artificial Intelligence 2026-02-17 v1 Software Engineering

Abstract

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

Keywords

Cite

@article{arxiv.2602.14865,
  title  = {EmbeWebAgent: Embedding Web Agents into Any Customized UI},
  author = {Chenyang Ma and Clyde Fare and Matthew Wilson and Dave Braines},
  journal= {arXiv preprint arXiv:2602.14865},
  year   = {2026}
}

Comments

Technical Report; Live Demo: https://youtu.be/Cy06Ljee1JQ

R2 v1 2026-07-01T10:38:43.920Z