{
  "added_at": "2026-10-16",
  "arxiv_id": "2509.24709",
  "arxiv_version_reviewed": "v3",
  "authors": [
    "Yang Chen",
    "Minghao Liu",
    "Yufan Shen",
    "Yunwen Li",
    "Tianyuan Huang",
    "Xinyu Fang",
    "Tianyu Zheng",
    "Wenxuan Huang",
    "Cheng Yang",
    "Daocheng Fu",
    "Jianbiao Mei",
    "Rong Wu",
    "Licheng Wen",
    "Xuemeng Yang",
    "Song Mao",
    "Qunshu Lin",
    "Zhi Yu",
    "Yongliang Shen",
    "Yu Qiao",
    "Botian Shi"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-iwr-bench.bib",
  "code_url": "https://github.com/SIGMME/IWR-Bench",
  "date_basis": "Publication year stated by the official ICLR proceedings; no finer publication date is asserted.",
  "date_basis_zh": "采用 ICLR 官方论文集标明的出版年份，不推定更精确的出版日期。",
  "date_precision": "year",
  "description_en": "Tests reconstruction of interactive webpages from user-interaction videos and supplied static assets. Its 113 tasks replay annotated action sequences to assess visual fidelity and functional behavior across observed page states.",
  "description_zh": "测试模型利用用户交互视频和提供的静态资源重建可交互网页的能力。其 113 项任务通过重放标注的操作序列，评估已观察页面状态的视觉保真度与功能行为。",
  "doi": null,
  "entry_url": "https://awesomerea.org/papers/paper-iwr-bench/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-iwr-bench/",
  "evidence_urls": [
    "https://proceedings.iclr.cc/paper_files/paper/2026/hash/55bfedfd31489e5ae83c9ce8eec7b0e1-Abstract-Conference.html",
    "https://proceedings.iclr.cc/paper_files/paper/2026/file/55bfedfd31489e5ae83c9ce8eec7b0e1-Paper-Conference.pdf",
    "https://arxiv.org/abs/2509.24709",
    "https://github.com/SIGMME/IWR-Bench",
    "https://github.com/SIGMME/IWR-Bench/blob/891ca67cbd940961245d3eea883f211637e03490/README.md",
    "https://sigmme.github.io/IWR-Bench/",
    "https://huggingface.co/datasets/IWR-Bench/IWR-Bench"
  ],
  "first_arxiv_date": "2025-09-29",
  "id": "paper-iwr-bench",
  "json_url": "https://awesomerea.org/papers/paper-iwr-bench/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-iwr-bench/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-iwr-bench/index.md",
  "metadata_notes": "Authors and order follow the published PDF: 20 authors. The proceedings landing page orders some middle authors differently; arXiv v3 and the project page list 21, additionally including Yunfei Zhao. The 2025 preprint date is separate from ICLR 2026 publication.",
  "metadata_notes_zh": "作者及顺序以正式发表的 PDF 为准，共 20 位。论文集网页的部分中间作者顺序不同；arXiv v3 和项目页列出 21 位，另含 Yunfei Zhao。2025 年预印本日期与 ICLR 2026 发表年份分开记录。",
  "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2026/file/55bfedfd31489e5ae83c9ce8eec7b0e1-Paper-Conference.pdf",
  "project_url": "https://sigmme.github.io/IWR-Bench/",
  "publication_date": null,
  "publication_status": "conference-paper",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "The required output is one HTML file; the paper explicitly instructs models to mock implied backend logic with static JavaScript data. Trajectory coverage and model-based judgments do not prove complete website or backend equivalence.",
  "scope_limitations_zh": "要求输出单个 HTML 文件；论文明确要求用 JavaScript 静态数据模拟隐含的后端逻辑。轨迹覆盖和模型评审均不能证明完整网站或后端等价。",
  "targets": [
    "website"
  ],
  "title": "IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?",
  "title_zh": "IWR-Bench：大型视觉语言模型能否根据用户交互视频重建可交互网页？",
  "url": "https://proceedings.iclr.cc/paper_files/paper/2026/hash/55bfedfd31489e5ae83c9ce8eec7b0e1-Abstract-Conference.html",
  "venue": "ICLR 2026",
  "verification": "source-reviewed",
  "verified_at": "2026-10-16",
  "why_fits_en": "Provides a direct behavioral reconstruction benchmark beyond static screenshots while making the frontend/backend boundary explicit.",
  "why_fits_zh": "提供超越静态截图的行为重建基准，同时明确前端与后端的能力边界。",
  "year": 2026
}