Search papers, labs, and topics across Lattice.
This paper introduces \textsc{Sieve}, a novel search--inspect--fetch strategy that leverages a Boolean Query Language (BQL) to enhance the retrieval process for deep-research agents by focusing on the structural elements of webpages. By filtering candidates based on titles, headings, and sections, \textsc{Sieve} significantly reduces irrelevant content and improves accuracy across three QA collections, outperforming conventional Search--Visit configurations while using 20.7% to 50.6% fewer tokens. The findings indicate that Boolean filtering enhances the performance of various rankers, maintaining accuracy advantages regardless of the retriever or agent backbone used.
\textsc{Sieve} achieves higher accuracy with significantly fewer tokens by intelligently filtering webpage content based on structure, revolutionizing how deep-research agents retrieve information.
Existing deep-research agents use a Search--Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata. This prevents agents from directly constraining retrieval to parts of a webpage and often carries irrelevant content into their context. We introduce \textsc{Sieve}, a search--inspect--fetch strategy driven by a Boolean Query Language (BQL): it searches webpage fields to filter candidates, uses an interchangeable ranker to order them, presents structure-rich result cards for inspection, and fetches only selected sections. Across three QA collections, \textsc{Sieve} is more accurate than the strongest conventional Search--Visit configuration on each collection while using $20.7$--$50.6\%$ fewer tokens. Boolean filtering improves every tested ranker, and the accuracy--context advantage persists across retriever choices and agent backbones. Our implementation is included in the SkimSearchAgent library at https://github.com/ielab/skim-search-agent.
