Paper Detail
Ziqi Zhang, Shaohui Li, Bing Li
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{zhang2026structured,
title = {Structured Interaction, Visual Localization, and Robust Execution for Complex Web Tasks: A Technical Report on the WebRetriever Challenge},
author = {Ziqi Zhang and Shaohui Li and Bing Li},
year = {2026},
abstract = {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 e},
url = {https://arxiv.org/abs/2609.35904},
keywords = {cs.IR, cs.MM},
eprint = {2609.35904},
archiveprefix = {arXiv},
}
{}