AwesomeREA.org

2025 · Conference paper

Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping

Jingyu Xiao; Yuxuan Wan; Yintong Huo; Zixin Wang; Xinyi Xu; Wenxuan Wang; Zhiyao Xu; Yuhang Wang; Michael R. Lyu

Benchmarks reconstruction of interactive webpages from screenshots before and after an interaction. The final study covers 127 webpages and 374 interactions, comparing rendered appearance, automated interaction checks, and human usability judgments.

Scope and limitations

The inputs specify individual interaction transitions, not autonomous exploration of a complete site. Its tests do not establish long-workflow, server-side, or original-source equivalence; a detectable interaction is not necessarily usable.

Why it fits this collection

Extends screenshot reconstruction with concrete behavioral checks, helping distinguish visual similarity from usable interaction.

Publication and review details

Venue
ASE 2025
Status
Conference paper
Publication / posting date
November 16, 2025
Date source
Publisher-deposited Crossref print-publication date; this also matches the conference start date.
First arXiv submission
November 5, 2024
arXiv
2411.03292
Reviewed arXiv version
v3
DOI
10.1109/ASE63991.2025.00028

Uses the final nine-author title and author list. The 2026 arXiv v3 revision is separate from the 2025 conference publication; the earlier preprint used a different title, five authors, and a smaller benchmark.

Sources reviewed

Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.

Primary sources

  1. https://doi.org/10.1109/ASE63991.2025.00028
  2. https://api.crossref.org/works/10.1109/ASE63991.2025.00028
  3. https://arxiv.org/abs/2411.03292
  4. https://arxiv.org/pdf/2411.03292v3
  5. https://github.com/WebPAI/Interaction2Code
  6. https://webpai.github.io/Interaction2Code/