Web Application Generation

Follow this topic Ask about this topic

This field studies how AI can build websites and web applications from prompts, screenshots, design references, and videos. Common approaches use large language and vision-language models to generate code, with agents that plan, edit, render, and test applications; reinforcement learning can also use browser-execution feedback as a training signal. Benchmarks increasingly test visual fidelity, requirement coverage, and multi-step browser interactions, alongside harder settings such as evolving applications and full-stack development. Models can produce usable interfaces, but visual quality does not guarantee correct behavior, and reliable state handling, integration, security, and long-horizon changes remain difficult.

Latest papers

41 papers7 papers in the last four weeks, up 133% on the four weeks before. 0.0% of all new papers.

WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
Apr 22, 2026Juyong Jiang, Chenglin Cai, Chansung Park +4RL for Code Generation RL for Language Models
The Hong Kong University of Science and Technology (Guangzhou) · Alibaba · Tongyi Lab, Alibaba Group +3
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
Apr 16, 2026Yan Li, Zezi Zeng, Yifan Yang +12Web Application Generation Web Agent Benchmarks
Shanghai Jiao Tong University · Xi’an Jiaotong University · Microsoft Corporation +1
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
Mar 27, 2026Zehai He, Wenyi Hong, Zhen Yang +4Web Agent Benchmarks Web Application Generation
Tsinghua University · Zhipu AI
PaperVoyager : Building Interactive Web with Visual Language Models
Mar 24, 2026Dasen Dai, Biao Wu, Meng Fang +1Web Application Generation Document Understanding
Vast Intelligence Lab · UTS · University of Liverpool
Interrogating Design Homogenization in Web Vibe Coding
Mar 13, 2026Donghoon Shin, Alice Gao, Rock Yuren Pang +3Web Application Generation Human-AI Co-Creation
University of Washington, Seattle, WA, USA · Microsoft Research & University of Washington, Seattle, WA, USA
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
Mar 10, 2026Zuhao Zhang, Chengyue Yu, Yuante Li +3Web Application Generation LLM Evaluation
Inclusion AI, Ant Group, Hangzhou, Zhejiang, China · Shanghai Jiao Tong University, Shanghai, China · Carnegie Mellon University, Pittsburgh, PA, USA
Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development
Mar 4, 2026Hung Tran, Langston Nashold, Rayan Krishnan +2Web Application Generation Code Generation Evaluation
Vals AI San Francisco, California, USA · Massachusetts Institute of Technology Cambridge, Massachusetts, USA
Generative UI: LLMs are Effective UI Generators
Feb 24, 2026Yaniv Leviathan, Dani Valevski, Matan Kalman +10Web Application Generation
Cheenu · Google Research
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
Jan 7, 2026Ziyun Zhang, Zezhou Wang, Xiaoyi Zhang +4Web Application Generation GUI Agents
1Peking University · 2Nanjing University · 3Microsoft Research Asia
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
May 23, 2025Haoyu Sun, Huichen Will Wang, Jiawei Gu +2Software Engineering Web Application Generation
Tongji University · Shanghai AI Laboratory · University of Washington +1
WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Development
Oct 24, 2024Shanchao Liang, Nan Jiang, Shangshu Qian +1Image-to-Code Generation Web Application Generation
Purdue University

Apr 22, 2026J/K move · Enter open · S save

WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning

Juyong Jiang, Chenglin Cai, Chansung Park, Jiasi Shen+3

The Hong Kong University of Science and Technology (Guangzhou) · Alibaba · Tongyi Lab, Alibaba Group+3

RL for Code Generation RL for Language Models Web Application Generation LLM Code Generation

Open paper AskPDF arXiv

While Large Language Models (LLMs) excel at function-level code generation, project-level tasks such as generating functional and visually aesthetic multi-page websites remain highly challenging. Existing works are often limited to single-page static websites, while agentic frameworks typically rely on multi-turn execution with proprietary models, leading to substantial token costs, high latency, and brittle integration. Training a small LLM end-to-end with reinforcement learning (RL) is a promising alternative, yet it faces a critical bottleneck in designing reliable and computationally feasible rewards for website generation. Unlike single-file coding tasks that can be verified by unit tests, website generation requires evaluating inherently subjective aesthetics, cross-page interactions, and functional correctness. To this end, we propose WebGen-R1, an end-to-end RL framework tailored for project-level website generation. We first introduce a scaffold-driven structured generation paradigm that constrains the large open-ended action space and preserves architectural integrity. We then design a novel cascaded multimodal reward that seamlessly couples structural guarantees with execution-grounded functional feedback and vision-based aesthetic supervision. Extensive experiments demonstrate that our WebGen-R1 substantially transforms a 7B base model from generating nearly nonfunctional websites into producing deployable, aesthetically aligned multi-page websites. Remarkably, our WebGen-R1 not only consistently outperforms heavily scaled open-source models (up to 72B), but also rivals the state-of-the-art DeepSeek-R1 (671B) in functional success, while substantially exceeding it in valid rendering and aesthetic alignment. These results position WebGen-R1 as a viable path for scaling small open models from function-level code generation to project-level web application generation.