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. 02751v1 Announce Type: cross Abstract: Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web sources expose through titles, headings, sections, and metadata.
By Shuai Wang, Haodong Chen, Yu Yin, Shengyao Zhuang, Bevan Koopman, Guido Zuccon
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. 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
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
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:2609.14412v1 Announce Type: new
Abstract: Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmar...
By Radin Hamidi Rad, Amin Bigdeli, Negar Arabzadeh, Sajad Ebrahimi, Charles L. A. Clarke, Benjamin C. M. Fung, Ebrahim Bagheri
The paper investigates how to improve large language model (LLM) based autonomous web agents by filtering irrelevant webpage content. The authors reproduce baseline models on the WebArena benchmark and identify failure modes caused by raw HTML input. They propose DeBERTa‑ and T5‑based retrieval models that rank HTML elements by relevance, fine‑tuned on Mind2Web data, and demonstrate that the DeBERTa model raises the LLaMA‑2‑70B agent’s success rate from 1.97% to 2.96%. Additionally, a zero‑shot ColBERT retriever achieves recall of 0.52 on Mind2Web and 0.47 on WebArena.
By Zhitong Guo, Jing Yu Koh, Ruiyu Li
arXiv:2606. 05241v1 Announce Type: cross Abstract: Public benchmarks enable fair and reproducible evaluation of LLM reasoning, but they become fragile for deep research agents that actively search the web during inference.
By Yongjie Wang, Xinyue Zhang, Kunhong Yao, Zhiwei Zeng, Kaisong Song, Jun Lin, Zhiqi Shen
arXiv:2608.29953v1 Announce Type: new
Abstract: Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce Search...
By Guransh Singh, Vishwajeet Kumar, Arkadeep Acharya, Adnan Qidwai, Jaydeep Sen, Sachindra Joshi
Clarify-Then-Search is a benchmark that tests whether large language models can ask clarification questions to improve the usefulness of deep search results. It uses 518 real-world query pairs from Baidu, where each intent query is paired with an underspecified version. The evaluation involves a clarifier asking up to three questions, a user answerer providing only explicit information, and a rewriter generating a new query that is then searched; performance is measured by a weighted nugget-recall score.
By Deqiang Huang, Jingbo Zhou, Xinjiang Lu, Tong Xu, Hua Wu, Enhong Chen
TRACE is a lightweight learned selector that ranks completed search trajectories by aggregating cross‑rollout evidence, preserving individual query and evidence occurrences while propagating information across shared content or document identity. Trained with answer‑level supervision over frozen text embeddings, TRACE selects an existing answer without additional search or autoregressive aggregation, and a single selector generalizes across rollout policies and agent backbones. Across six WebQA policies, six long‑horizon dataset‑backbone combinations, and multiple WebQA benchmarks, TRACE outperforms majority voting and generative aggregators, achieving higher accuracy and at least tenfold higher processing throughput.
By Qisheng Zhou, Zhen Xiong, Qiaoyu Tan