📄Papers

Generative UI: LLMs are Effective UI Generators

Leviathan et al. (Google)

2025-11

परिचय

Google Research paper जिसने पहली बार Generative UI concept को व्यवस्थित रूप से रखा। Paper Generative UI को "AI models generating not just content, but the entire user experience" के रूप में define करता है। Experiments दिखाते हैं कि सही prompts और tools के साथ LLMs high-quality custom interactive interfaces बना सकते हैं जिन्हें human users काफी पसंद करते हैं—44% मामलों में human experts के बराबर। Paper generated interfaces के evaluation के लिए PAGEN dataset भी जारी करता है।

सारांश

मुख्य निष्कर्ष:

1. Definition: Generative UI में AI models केवल content नहीं, पूरा user experience बना सकते हैं
2. Effectiveness: LLMs 44% मामलों में human experts के बराबर high-quality interactive interfaces बना सकते हैं
3. PAGEN Dataset: Generated interfaces के systematic evaluation के लिए जारी किया गया
4. Approach: LLM interface generation को guide करने के लिए structured prompts और tools इस्तेमाल करता है
5. Implications: UI design को pre-built templates से dynamic, context-aware generation की ओर ले जाता है

मिलते-जुलते लेख

📄Papers

Toward Frontier-Quality Declarative UI Generation at Small-Model Cost

September 2026 Harness4GenUI paper studying whether small language models can generate production-oriented A2UI from approved component catalogs. Across task-management and cloud-console domains, the authors compare training-data strategies, model sizes, catalog sizes, cost, latency, binding correctness, and rendered quality.

a2uismall-language-modelssupervised-fine-tuning

लेखक Yang Y. et al. · 2026-09

EvoGenUI-Bench: Evaluating Multi-Turn Generative UI Assistants

August 2026 benchmark testing whether LLM assistants can maintain one executable web interface as user requirements evolve. EvoGenUI-Bench contains 150 five-turn tasks across information presentation, stateful interaction, and tool-grounded external state, with browser-based evaluation over screenshots, DOM and source evidence, actor traces, and runtime logs.

generative-uimulti-turnbenchmark

लेखक Peng Y. et al. · 2026-08

Maru: Information Architecture for Aligned, Persistent Generative UI

August 2026 HCI paper introducing information architecture as shared state for Generative UI. Maru captures how users partition, order, name, and prioritize information, turns those choices into persistent rules, and applies them across successive interface generations instead of rebuilding structure from each prompt.

generative-uiinformation-architecturepersonalization

लेखक Kim E. et al. · 2026-08

Awesome Generative UI