Generative UI: LLMs are Effective UI Generators
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917399927717888 |
|---|---|
| author | Leviathan, Yaniv Valevski, Dani Kalman, Matan Lumen, Danny Segalis, Eyal Molad, Eyal Pasternak, Shlomi Natchu, Vishnu Nygaard, Valerie Srinivasan Venkatachary Manyika, James Matias, Yossi |
| author_facet | Leviathan, Yaniv Valevski, Dani Kalman, Matan Lumen, Danny Segalis, Eyal Molad, Eyal Pasternak, Shlomi Natchu, Vishnu Nygaard, Valerie Srinivasan Venkatachary Manyika, James Matias, Yossi |
| contents | AI models excel at creating content, but typically render it with static, predefined interfaces. Specifically, the output of LLMs is often a markdown "wall of text". Generative UI is a long standing promise, where the model generates not just the content, but the interface itself. Until now, Generative UI was not possible in a robust fashion. We demonstrate that when properly prompted and equipped with the right set of tools, a modern LLM can robustly produce high quality custom UIs for virtually any prompt. When ignoring generation speed, results generated by our implementation are overwhelmingly preferred by humans over the standard LLM markdown output. In fact, while the results generated by our implementation are worse than those crafted by human experts, they are at least comparable in 50% of cases. We show that this ability for robust Generative UI is emergent, with substantial improvements from previous models. We also create and release PAGEN, a novel dataset of expert-crafted results to aid in evaluating Generative UI implementations, as well as the results of our system for future comparisons. Interactive examples can be seen at https://generativeui.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09577 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generative UI: LLMs are Effective UI Generators Leviathan, Yaniv Valevski, Dani Kalman, Matan Lumen, Danny Segalis, Eyal Molad, Eyal Pasternak, Shlomi Natchu, Vishnu Nygaard, Valerie Srinivasan Venkatachary Manyika, James Matias, Yossi Human-Computer Interaction Artificial Intelligence Computation and Language Machine Learning AI models excel at creating content, but typically render it with static, predefined interfaces. Specifically, the output of LLMs is often a markdown "wall of text". Generative UI is a long standing promise, where the model generates not just the content, but the interface itself. Until now, Generative UI was not possible in a robust fashion. We demonstrate that when properly prompted and equipped with the right set of tools, a modern LLM can robustly produce high quality custom UIs for virtually any prompt. When ignoring generation speed, results generated by our implementation are overwhelmingly preferred by humans over the standard LLM markdown output. In fact, while the results generated by our implementation are worse than those crafted by human experts, they are at least comparable in 50% of cases. We show that this ability for robust Generative UI is emergent, with substantial improvements from previous models. We also create and release PAGEN, a novel dataset of expert-crafted results to aid in evaluating Generative UI implementations, as well as the results of our system for future comparisons. Interactive examples can be seen at https://generativeui.github.io |
| title | Generative UI: LLMs are Effective UI Generators |
| topic | Human-Computer Interaction Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2604.09577 |