Skip to content

2026arXiv (accepted to EACL 2027 Main Conference)LongSearch agentscited 5×First author

Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agents

Shuai Wang, Haodong Chen, Yu Yin, Shengyao Zhuang, Bevan Koopman, Guido Zuccon

arXiv preprint (2026) (accepted to EACL 2027 Main Conference)

Paper ↗Project site ↗

Abstract

Existing deep-research agents typically follow a search-visit workflow that retrieves whole webpages without using the structure already exposed by titles, headings, sections, and metadata. This limits the agent’s ability to target specific parts of a page and often sends unnecessary content into the context window. In this work, we introduce Sieve, a search-inspect-fetch strategy built around a Boolean Query Language (BQL). It filters candidates with field-aware Boolean search, ranks them, presents structure-rich inspection cards, and fetches only the selected sections. Across three question-answering collections, Sieve is more accurate than a strong conventional search-visit baseline while using substantially fewer tokens. The implementation is released in the SkimSearchAgent project.

Cite · BibTeX
@misc{wang2026search,
  title = {{Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agents}},
  author = {Shuai Wang and Haodong Chen and Yu Yin and Shengyao Zhuang and Bevan Koopman and Guido Zuccon},
  howpublished = {arXiv preprint (2026) (accepted to EACL 2027 Main Conference)},
  year = {2026},
  url = {https://arxiv.org/abs/2608.02751}
}

Part of project