📄

Generative UI Papers - Google Research, PAGEN, A2UI & HCI Studies

Read foundational Generative UI papers, including Google Research's LLM UI generator work, the PAGEN dataset, A2UI personal-agent research, CHI/DIS HCI studies, and definitions of GenUI.

21 items
📄Papers

TaskArtisan: Designing Composable Generative Widgets for LLM-Assisted Analysis

July 2026 HCI paper examining how Generative UI can make long, multi-step chatbot analysis workflows easier to revisit and reuse. TaskArtisan lets people create analysis widgets and compose them into sequential or fan-out workflows, then compares the approach with a conventional chatbot in a 12-participant study.

generative-widgetsanalysiscomposition
by Chen M. and Pavel A. · 2026-07
Read More
📄Papers

AI Prototyper: A Figma Plugin for Decomposition-Based GUI Prototyping with LLMs

July 2026 paper introducing AI Prototyper, an open-source Figma plugin that turns natural-language screen descriptions into fully editable prototypes. Its pipeline decomposes a request into reviewable features, retrieves components from a fixed 32-primitive library, generates schema-constrained instances, and renders native Figma layers with auto-layout.

figmadesign-timegui-prototyping
by Salangsingha T. et al. · 2026-07
Read More
📄Papers

Spatula: Exploring On-Demand In-Situ Interfaces and Interaction for Attribute Control

July 2026 HCI paper introducing Spatula, an LLM-powered system that generates context-aware controls directly on a motion-graphics canvas. Its elastic attribute control space supports progressive discovery, multiple levels of precision, semantic group editing, and new controls on demand.

on-demand-uicreative-toolsdirect-manipulation
by Li B. et al. · 2026-07
Read More
📄Papers

Rethinking the UI of GenUI: A Tale of Two Designs

June 2026 HCI paper comparing the prompt-first, depth-first, high-fidelity pattern common in Generative UI tools with a structured, breadth-first, low-fidelity alternative. A study with 24 UX designers and product managers surfaces concrete trade-offs for early-stage design exploration.

ux-designdesign-explorationgenui
by Chen X. et al. · 2026-06
Read More
📄Papers

The Missing Layer: Why EdTech Needs Design-Time Generative UI, Not Just Runtime Personalization

June 2026 arXiv paper accepted at the AIED NextGen Learning Interfaces Workshop. It argues that adaptive education should use Generative UI at authoring time, not only at learner runtime, so instructors can verify accessible, modality-specific representations before students encounter them.

educationdesign-timeaccessibility
by Neshaei S. P. et al. · 2026-06
Read More
📄Papers

TaskLens: Generating Task-Conditioned Scaffolded Interfaces for Learning Professional Creative Software

DIS 2026 / arXiv paper introducing TaskLens, an LLM-based method that generates task-conditioned scaffolded UIs for complex creative tools. The system identifies workflow stages and domain concepts, selects relevant tools, generates implementation code, and produces interfaces that progressively disclose advanced features inside software such as Blender.

scaffolded-uicreative-softwaregenui
by Liu Y. et al. · 2026-06
Read More
📄Papers

Macaron-A2UI: A Model for Generative UI in Personal Agents

Fresh 2026 arXiv paper focused on runtime Generative UI for personal agents. The authors argue that plain chat becomes a bottleneck for complex agent tasks, introduce a large-scale Generative UI corpus plus A2UI-Bench, and train models that generate natural language together with lightweight executable UI actions for confirmation, preference refinement, and multi-goal coordination.

agentsa2uibenchmark
by Kong F. et al. · 2026-05
Read More
📄Papers

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.

personalizationgenuiarxiv
by Peng Y.-H. et al. · 2026-04
Read More
📄Papers

MAIC-UI: Making Interactive Courseware with Generative UI

Recent arXiv paper introducing a zero-code GenUI system for educational courseware. MAIC-UI turns textbooks, PPTs, and PDFs into interactive learning pages, uses a generate-verify-optimize pipeline for pedagogical accuracy, and supports click-to-locate incremental edits instead of expensive full regeneration.

educationcoursewaregenui
by Tu S. et al. · 2026-04
Read More
📄Papers

Generative UI as an Accessibility Bridge: Lessons from C2C E-Commerce

arXiv / CHI 2026 workshop paper arguing that runtime Generative UI can close accessibility gaps in user-generated marketplace content. Drawing on six studies with blind, low-vision, and older adult users, it frames adapted interfaces, audio guidance, and regenerated HTML as policy-driven accessibility interventions rather than cosmetic UI variants.

accessibilityruntime-adaptationecommerce
by Bektur Ryskeldiev · 2026-04
Read More
📄Papers

What does Generative UI mean for HCI Practice?

CHI EA 2026 workshop paper from Microsoft Research and academic HCI researchers on how AI-generated interfaces may reshape design methods, workflows, and user experiences. It is useful because it frames GenUI as a practice-level shift for researchers, designers, developers, and product teams, not only a model-output technique.

chi-2026hci-practicedesign-workflows
by Lindley S. et al. · 2026-04
Read More
📄Papers

Software as Content: Dynamic Applications as the Human-Agent Interaction Layer

2026 arXiv paper arguing that chat alone is a poor medium for structured, stateful human-agent work. The authors propose Software as Content, where dynamically generated agentic applications become the primary interaction layer, persist across turns, and expose actionable controls instead of forcing everything through linear text.

agentic-appsgenuistateful-ui
by Xie M. and Xie Y. · 2026-03
Read More
📄Papers

The Keyhole Effect: Why Chat Interfaces Fail at Data Analysis

2026 arXiv paper arguing that chat is a poor default surface for multi-step, stateful analysis work. It gives a cognitive-science account of where linear conversations break down, then positions Generative UI and other hybrid interaction patterns as practical ways to restore visibility, spatial memory, and user control.

genuihybrid-uianalysis
by Mohan Reddy · 2026-02
Read More
📄Papers

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.

malleable-softwaregenuihci
by Min B. et al. · 2026-01
Read More
📄Papers

AlignUI: A Method for Designing LLM-Generated UIs Aligned with User Preferences

2026 arXiv paper on aligning LLM-generated interfaces with user tasks and preferences. The authors collect 720 UI-control preferences from 50 users across image-editing tasks, use that dataset to guide model reasoning, and evaluate generated UIs with 72 additional users.

preference-alignmentllm-generated-uihci
by Liu Y. et al. · 2026-01
Read More
📄Papers

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.

googlegenerative-uillm
by Leviathan et al. (Google) · 2025-11
Read More
📄Papers

Improving User Interface Generation Models from Designer Feedback

Research paper on training LLM-based UI generators with feedback that matches professional design practice. The authors compare rankings, comments, sketches, and direct revisions from 21 designers, then use the resulting data to improve code models that generate rendered interfaces.

ui-generationdesigner-feedbackmodel-alignment
by Wu J. et al. · 2025-09
Read More
📄Papers

Generative Interfaces for Language Models

ACL 2026 Findings paper proposing a paradigm where LLMs proactively generate task-specific interfaces instead of replying only with text. The work pairs interface-specific representations with iterative refinement and reports that human evaluators preferred generative interfaces over conversational ones by up to 72% across information-dense and exploratory tasks.

acl-2026evaluationgenui
by Chen J. et al. · 2025-08
Read More
📄Papers

Towards a Working Definition of Designing Generative User Interfaces

DIS 2025 conference paper that proposes the first working definition of Generative UI (GenUI) through literature review and case analysis. The research identifies GenUI as a new paradigm of interface creation where "humans and AI collaborate at design-time to generate interfaces, and users interact with AI-generated interfaces at runtime". The paper summarizes five key characteristics of GenUI: co-creation, design space expansion, representational fluidity, contextual adaptation, and generation-first.

dis-2025genuidefinition
by Lee K.-H. · 2025-05
Read More
📄Papers

Generative and Malleable User Interfaces with Generative AI

CHI 2025 paper that proposes using AI to generate "generative and malleable user interfaces" based on user tasks. The authors designed a task-driven data model where LLMs parse user prompts and generate UI specifications, then map them to concrete interfaces. Experiments demonstrate that this method can dynamically generate interface elements such as forms and visualizations, supporting users to modify interfaces via natural language.

chi-2025malleable-uitask-driven
by Cao Y. et al. · 2025-03
Read More
📄Papers

BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks

VL/HCC 2024 paper from Apple researchers introducing BISCUIT, a JupyterLab workflow that inserts an ephemeral UI layer between user intent and LLM-generated code. Instead of jumping straight from prompt to source files, users first interact with temporary generated controls that help them understand options, refine requests, and explore variables before code is emitted.

notebooksephemeral-uiprogramming
by Cheng R. et al. · 2024-08
Read More

A curated collection of Generative UI resources.

Made with ❤️ by the community