The paper introduces Sieve, a search‑inspect‑fetch framework that leverages a Boolean Query Language (BQL) to target specific webpage fields, rank candidates, present structure‑rich result cards, and fetch only selected sections. Compared to traditional Search‑Visit agents, Sieve achieves higher accuracy across three QA collections while reducing token usage by 20.7–50.6%. Boolean filtering consistently improves performance for all tested rankers and remains effective across different retrievers and agent backbones.
By Shuai Wang, Haodong Chen, Yu Yin, Shengyao Zhuang, Bevan Koopman, Guido Zuccon
arXiv:2608. 02751v2 Announce Type: replace-cross Abstract: 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.
By Shuai Wang, Haodong Chen, Yu Yin, Shengyao Zhuang, Bevan Koopman, Guido Zuccon
arXiv:2605. 06647v2 Announce Type: replace-cross Abstract: Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet most treat retrieval as a black box: they issue exploratory queries, inspect snippets, and reformulate until evidence emerges.
By Zeyu Yang, Qi Ma, Jason Chen, Anshumali Shrivastava
arXiv:2607. 26070v1 Announce Type: cross Abstract: Large language model (LLM)-based agentic search systems are often evaluated as if the underlying LLM were the only component that matters, yet their measured performance also depends on the surrounding search environment: the Wikipedia snapshot, preprocessing pipeline, chunking policy, retrieval backend, tool schema, observation format, and answer submission rule.
By Guanming Xiong, Penghui Zhang
Q2D-Web is a new large‑scale benchmark for agentic Retrieval‑Augmented Generation (RAG) systems, featuring a 190 million‑document web corpus and 70 k machine‑reformulated search queries in ten languages. It supplies three sets of relevance judgments—agent citations, production rankings, and a combined set enriched with LLM‑based labels—to evaluate first‑stage retrievers. Experiments on 13 retrievers show consistent ranking across judgment sets but significant variation across domains, languages, and query types, and demonstrate that a carefully sampled sub‑corpus can approximate full‑corpus evaluation with minimal loss in Recall@1000.
arXiv:2607.10198v2 Announce Type: replace
Abstract: Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these in...
By Sriram Selvam, Anneswa Ghosh