GUIDE (GenUI Development Environment), a system that lets designers continuously inspect and refine GenUI behavior as they create and edit interfaces through prompt optimization and a novel adaptive conformance scoring model, is introduced.
Abstract
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 design.md.
A persona-driven, multi-agent workflow in which User-Agents execute Perceive–Decide–Act loops on rendered prototypes while a Supervisor-Agent verifies trace integrity and maps evidenced failures to established standards (ISO 9241-110 and Nielsen’s heuristics).
Oussama Touir, Farah Barika Ktata, M. Soui· 0 citations
Despite skepticism surrounding the integration of Generative AI (GenAI) into creative domains, its potential to transform Computer-Aided Design (CAD) workflows remains largely underexplored. In this study, we investigate how professional 3D CAD designers envision and evaluate GenAI-supported design processes. Using a “...
Emily Kuang, J. Vermeulen, George W. Fitzmaurice et al.· ACM Transactions on Computer...· 0 citations
This work designed a tool called dBlocks with the following features: blocks to scope content, a context manager to edit context, and inline execution to verify code, and shows how human-centered design can guide the development of LLM-integrated tools.
A scalable framework for Constrained AI-Assembled Graphical User Interfaces (GUIs) that dynamically assembles the interface at runtime from a pre- validation library of components using an LLM is proposed.
Akshil Shah, Sebastian Zepf, Andreas Riener· Proceedings of the 18th Inte...· 0 citations
Generative user interfaces (GenUI) promise personalized interfaces to a user's tasks and needs. However, user needs are often implicit---difficult for systems to infer and users to articulate, making it hard for users to arrive at their ideal interface. We propose Elicitive User Interfaces, a design approach to GenUI t...
Eunhye Kim, Bryan Min, Hai-Jun Xia et al.· 0 citations
This review synthesizes the characteristics, benefits and drawbacks of various procedural generation methods, helping developers choose the most appropriate technique based on a particular use case.
Robert Andrei Caragicu, Anca Morar, A. Moldoveanu et al.· IEEE Access· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026
Founded by Anthony Jules ’92, SM ’92 and Professor Emeritus Rodney Brooks, Robust AI’s robots are designed to collaborate with humans in factories and warehouses.
MIT News · Artificial Intelligence· news.mit.eduNov 12, 2026
MIT scientists developed a training method to generate models that simulate the effects of human activities on climate much more quickly than other approaches.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.