NeFut Logo NeFut
Admin Login

[CS.AI] LongWebBench: A Revolutionary Benchmark for Long Webpage Generation

Published at: 2026-06-17 22:00 Last updated: 2026-06-20 13:46
#AI #Machine Learning #Open Source

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. We introduce LongWebBench, a benchmark for evaluating long-horizon webpage generation from both structural and functional perspectives.

LongWebBench contains 490 real-world long webpages for structural fidelity evaluation and 507 goal-oriented interaction tasks over 129 webpages for functional evaluation. It employs two complementary protocols: a multi-dimensional VLM-based metric for assessing long-range structural coherence, and a DOM-augmented agent-based pipeline for end-to-end functional verification. We further examine the automatic evaluation protocols through human agreement analysis.

Experiments with state-of-the-art open-source and proprietary VLMs under single-image and multi-image settings reveal that structural fidelity degrades as webpage length increases, while visually plausible generations often fail to support executable multi-step interactions. These results highlight the need to evaluate long webpage generation beyond visual similarity, with executable interaction as a core criterion.

Our code and data are available at GitHub.

Blogger's Review: The introduction of LongWebBench marks a significant advancement in the evaluation of webpage generation, particularly in real-world applications involving long webpages. By assessing both structural and functional aspects, it provides a comprehensive understanding of VLM performance in complex interactions, paving the way for deeper future research.

Original Source: https://arxiv.org/abs/2606.17727

[h] Back to Home