Papers
Academic research and technical papers on Generative UI
Cases
Real-world products and applications using Generative UI
Videos
Tutorials, demos, and talks about Generative UI
Resources
Blogs, documentation, and open-source projects
Discussions
Community forums and popular discussion threads
Latest Resources
Efficient Personalization of Generative User Interfaces
Recent arXiv paper on one of the core unsolved GenUI problems: personalization. The authors collect pairwise judgments from trained designers over the same 600 generated UIs, show that design preferences diverge substantially, and propose a sample-efficient preference model that personalizes generated interfaces better than baseline evaluators and direct prompting.
A2UI v0.9: The New Standard for Portable, Framework-Agnostic Generative UI
Official Google Developers Blog update on A2UI v0.9. The post positions A2UI as a production-oriented standard for declarative, agent-generated UI, adds the official React renderer, and explains how agents can target existing component catalogs across web and mobile without generating arbitrary frontend code.
Stop making AI write JSON - Why we built OpenUI
OpenUI's official engineering write-up on why the team moved beyond JSON trees for Generative UI. It lays out the runtime requirements for interactive agent-generated interfaces, argues that nested JSON becomes fragile for stateful UI, and introduces OpenUI Lang as a streaming-first language for model-generated UI.
Introducing Tambo 1.0
Official Tambo launch post for its production-ready React generative UI toolkit. The post explains the fullstack model: developers register existing React components, the agent selects and streams props into them, and Tambo handles conversation state, orchestration, and persistent interactive component behavior.
Gradual Generation of User Interfaces as a Design Method for Malleable Software
2026 arXiv paper proposing "Gradually Generating User Interfaces", a GenUI design method that inserts intermediate interface layers during generation so users can discover and control customization options without being overwhelmed by a giant prompt box or dense menu system.
Introducing A2UI: An open project for agent-driven interfaces
Official Google Developers Blog announcement for A2UI, a portable declarative format for agent-generated interfaces. It explains how remote or local agents can request trusted UI components from a host app instead of emitting arbitrary HTML, making Generative UI safer, cross-platform, and incrementally updateable.
Generative UI: LLMs are Effective UI Generators
Google Research paper that first systematically articulates the Generative UI concept. The paper defines Generative UI as "AI models generating not just content, but the entire user experience". Experiments show that with the right prompts and tools, LLMs can generate high-quality custom interactive interfaces that are significantly preferred by human users (44% of cases comparable to human experts). The paper also releases the PAGEN dataset for evaluating generated interfaces.
Google Gemini 3 - Dynamic View & Visual Layout
Google has implemented Generative UI features in Gemini 3 (internally called "Dynamic View" and "Visual Layout" experiments). According to Google's official blog, Gemini 3 AI Mode can "generate immersive visual layouts and interactive tools and simulations", completely generating interfaces on-the-fly based on user queries. Dynamic View allows Gemini 3 to "design and code a fully custom interactive response" for each prompt, while Visual Layout generates "magazine-style" immersive multimedia interfaces.
Google Search AI Mode
With Gemini 3 launching in Search, AI Mode has added Generative UI experiences. Google Search team states that Gemini 3 in search can dynamically create ideal visual layouts with interactive tools and simulations, tailoring interfaces to user questions. For example, when searching for complex concepts, users not only get text answers but can also see dynamic charts or simulation tools (like calculators with real-time adjustable parameters).