Metraipolis › archive › dc_e57a771bc362

Structured Interaction, Visual Localization, and Robust Execution for Complex Web Tasks: A Technical Report on the WebRetriever Challenge — arXiv:2609.35904

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35904
License (as archived)
CC0-1.0
Archived
2026-10-07T18:37:44.426Z
SHA-256 of the archived text
da946c18847db3a3279d8dab509076c96c29bfcfa9356db6cb22dc376d69e9f3
Stable URL of this page
https://metraipolis.com/documento/dc_e57a771bc362

How to cite

Structured Interaction, Visual Localization, and Robust Execution for Complex Web Tasks: A Technical Report on the WebRetriever Challenge — arXiv:2609.35904 — arXiv (en), https://arxiv.org/abs/2609.35904 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e57a771bc362 (Metraipolis archive dc_e57a771bc362, sha256 da946c18847db3a3279d8dab509076c96c29bfcfa9356db6cb22dc376d69e9f3)
BibTeX
@misc{dce57a771bc362,
  title = {Structured Interaction, Visual Localization, and Robust Execution for Complex Web Tasks: A Technical Report on the WebRetriever Challenge — arXiv:2609.35904},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35904},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e57a771bc362; sha256 da946c18847db3a3279d8dab509076c96c29bfcfa9356db6cb22dc376d69e9f3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35904. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This report presents the web agent system developed for the WebRetriever Challenge. The system follows a structuredinteraction- first strategy, using semantic webpage information for routine browser operations and invoking visual perception only when structured representations are insufficient. Three key designs are introduced: grid-assisted visual localization for difficult-to-access controls, hierarchical context management for reducing redundant page and interaction history, and fault-aware execution mechanisms for stable multi-browser task processing. The system achieved a pass rate of up to 79% in local evaluation on Protocol 1. In the official Protocol 3 competition, it achieved a 59% pass rate with eight concurrent browser workers and ranked first overall, winning the WebRetriever Challenge.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR) ; Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2609.35904 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T18:04:00.981Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).