Metraipolis › archive › dc_b0b709d306fc

GUIDE: Designer-in-the-loop Authoring of Conformant Generative User Interfaces — arXiv:2609.21285

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21285
License (as archived)
CC0-1.0
Archived
2026-10-10T01:44:07.321Z
SHA-256 of the archived text
043879dc02b3a47c0c3ba5b2ab420f9d861d74023a7b98be5e3459a96661cbb6
Stable URL of this page
https://metraipolis.com/documento/dc_b0b709d306fc

How to cite

GUIDE: Designer-in-the-loop Authoring of Conformant Generative User Interfaces — arXiv:2609.21285 — arXiv (en), https://arxiv.org/abs/2609.21285 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b0b709d306fc (Metraipolis archive dc_b0b709d306fc, sha256 043879dc02b3a47c0c3ba5b2ab420f9d861d74023a7b98be5e3459a96661cbb6)
BibTeX
@misc{dcb0b709d306fc,
  title = {GUIDE: Designer-in-the-loop Authoring of Conformant Generative User Interfaces — arXiv:2609.21285},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21285},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b0b709d306fc; sha256 043879dc02b3a47c0c3ba5b2ab420f9d861d74023a7b98be5e3459a96661cbb6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21285. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative User Interfaces (GenUIs) enable applications to generate interfaces on demand from user needs and context. Like conventional UIs, they must still reflect designers' intent and conform to requirements such as brand identity. Unlike conventional UIs, designers cannot directly specify or see every interface a GenUI may produce, making design intent harder to enforce. We introduce GUIDE (GenUI Development Environment), a system that lets designers continuously inspect and refine GenUI behavior as they create and edit interfaces. GUIDE uses designers' modifications and interactions to adapt GenUIs through prompt optimization and a novel adaptive conformance scoring model. We validate GUIDE's scoring model and system. The scoring model matched or outperformed proprietary LLM baselines on held-out comparisons of real and synthetic application screens. In a study with 12 UI/UX practitioners, participants found GUIDE effective and usable and significantly preferred aligned outputs over a strong baseline using exemplars and a model-generated this http URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.21285 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T01:13:57.205Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).