WebUIProof is a new execution‑oriented benchmark for WebUI code generation that supplies structured specifications and dense, executable interaction tests across general WebUIs and 3D interactive simulations. It employs a UI‑agent harness that runs tests in a headless browser using a plan–act–observe loop to locate DOM elements, perform actions, observe changes, and verify assertions. Evaluations on eight commercial LLMs reveal frequent interaction‑based failures, especially on 3D interfaces, and demonstrate that training compact models with RL rewards from these tests improves functional completion and reduces build failures.
By Yun-Yun Tsai, Yuning Mao, Shiqi Wang, Junfeng Yang, Sinong Wang
arXiv:2608.30530v1 Announce Type: new
Abstract: VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility...
By Jiajun Wu, Jian Yang, Yaxin Du, Wei Zhang, Haowen Wang, Junhang Cheng, Yuxuan Zhang, Tuney Zheng, Xianglong Liu, Ming Zhou
RILA is an execution‑driven agent that integrates browser rendering into the generation loop for interactive web development. It uses an Action Interaction Verification module to replay reference interactions on generated pages, collecting execution‑aware observations, and an Execution‑aware Rendering Score to jointly assess interaction correctness and visual fidelity during iterative optimization. A data synthesis pipeline further augments training data, enabling RILA to significantly improve interaction and visual quality across foundation models, even outperforming larger one‑shot generators.
By Yilong Guo, Hanqi Chen, Zixiao Ye, Guanzhong Wang, Chen Yu, Zeyu Chen
arXiv:2606. 17727v1 Announce Type: new Abstract: Recent vision-language models (VLMs) have shown promising progress in generating webpages from visual inputs, yet existing evaluations mainly focus on short, single-screen, and largely static webpages.
By Yi Zhao, Zhen Yang, Mengpan Chen, Mingde Xu, Shanghui Gong, Xijun Liu, Jibing Gong, Jie Tang
arXiv:2608.29387v1 Announce Type: new
Abstract: Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests...
By Yue Peng, Lanke Xia, Zihan Wang, Jiahao Ye, Ke Ning, Hongyi Wen
arXiv:2609.15387v3 Announce Type: replace-cross
Abstract: Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automat...
By Chenxu Liu, Zilu Zou, Peizhong Gao, Jiawen Tao, Zhexin Zhang, Guang Chen, Haowei Lin, Ying Zhou, Tianyi Bai, Dolly Deng, Suncong Zheng, Maxm Pan
arXiv:2610.03036v1 Announce Type: cross
Abstract: We present WebFovea, a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 with a final score of 57.0 out of 100. The challenge...
By Jiangang Han
arXiv:2609.15387v1 Announce Type: cross
Abstract: Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automated evalu...
By Chenxu Liu, Zilu Zou, Peizhong Gao, Jiawen Tao, Zhexin Zhang, Guang Chen, Haowei Lin, Ying Zhou, Tianyi Bai, Dolly Deng, Suncong Zheng, Maxm Pan
Large language models (LLMs) have demonstrated growing competence in web page generation. However, existing text-driven approaches rely on complex prompts that impose substantial demands on users and offer limited expressivity for page layout and cross-page visual coherence.
ComponentBench is a new benchmark that evaluates computer‑use agents at the component level on modern web UIs. It contains 97 canonical UI components and 2,910 programmatically verified tasks, along with cleaned human reference trajectories for measuring task success and interaction efficiency. The benchmark also offers a scalable pipeline for auditing structural difficulty and synthesizing failure analyses across tasks and component families.
By Tianchen Guan, Xinlei Lin, Royce Cheng-Yue, Xiangjun Wang, Shuyan Zhou
ChainWorld is a new benchmark that composes atomic OSWorld tasks into long‑horizon desktop workloads, creating 347 chains of length two to four that compare two renderings of the same task sequence. In single‑turn evaluation all tasks are presented together in one prompt, while in multi‑turn evaluation tasks are revealed one at a time. Across four current computer‑use agents, maximum chain completion is 31 %, with multi‑turn evaluation improving completion for three models but both protocols remaining challenging and exposing different failure profiles.
By Vincent Siu, Manasi Sharma, Dawn Song, Daniel Yue Zhang, Chenguang Wang, Ying Liu
arXiv:2607. 06306v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated growing competence in web page generation.
By Grace Man Chen, Litao Guo, Yifan Wu, Yiyu Chen, Yenchi Tseng, Sicheng Liu, Yuyu Luo, Ying-Cong Chen