@inproceedings{zhang-etal-2026-web,
    title = "Web Sitemap Knowledge Can Enhance Autonomous Browsing",
    author = "Zhang, Yuyao  and
      Lu, Hongyu  and
      Jin, Jiajie  and
      Qian, Hongjin  and
      Li, Shiyu  and
      Yang, Zhao  and
      Zhu, Yutao  and
      Wen, Ji-Rong  and
      Dou, Zhicheng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1465/",
    pages = "29307--29321",
    ISBN = "979-8-89176-395-1",
    abstract = "Recent advances in large language models (LLMs) have enabled web agents to perform interactive tasks on real-world websites. However, existing agents still suffer from limited robustness, efficiency, and task success, largely due to their lack of structural understanding of websites and the absence of browsing priors in pre-trained models. To address these challenges, this paper proposes the Web Agent Sitemap Protocol (WASP), an agent-oriented sitemap that integrate structured website knowledge into web agents. WASP adopts a dual-granularity design, providing global site-level structure and local page-level semantic and interaction guidance. We also introduce a framework LightASM for constructing such sitemaps by identifying core pages and generating concise semantic summaries and block-level descriptions. Experiments on real-world browsing benchmarks demonstrate that WASP substantially improves the robustness, efficiency, and effectiveness of LLM-based web agents without extra training."
}