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
The paper presents an adaptive browserless system for extracting prices from e‑commerce websites, improving robustness to structural differences. It combines HTML fragmentation with syntactic, semantic, and frequency rules, then enhances the baseline with a Bayesian weight‑update and a genetic‑algorithm parameter optimizer. The hybrid approach raises precision from 77.2% to 87.3% and cuts per‑page processing time by about 14%, positioning it as a competitive, low‑cost alternative to manual wrappers, browser‑based, or LLM‑driven methods.
By Evgeniia Kositsyna, Jorge Lloret-Gazo
arXiv:2607. 00007v1 Announce Type: cross Abstract: Large language model (LLM)-based web agents reduce manual scripting for web data collection, yet on live websites, they often miss relevant pages, return incomplete multimodal outputs, or return media URLs that are not directly downloadable.
By Soojeong Lee, Joseph Lee, Yongseong Cho, Sunjae Kim, Youngwoo Moon, Kyungwoo Song
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
arXiv:2607. 29677v1 Announce Type: new Abstract: Enterprise workflows increasingly rely on agents for \emph{schema-guided extraction}: given a document and a user-defined schema, the agent faithfully follows the schema to produce the correct output with source evidence as grounding metadata.
By Boyang Zhang, Adrian Lyjak, Eli Stewart, Zhaoqi Li, Simon Suo
PACE is an agentic framework that learns publisher‑specific extraction configurations from representative web pages and user requirements. During training it employs LLMs to analyze page structure and gather reusable extraction patterns, then creates a deterministic extractor template for inference that eliminates the need for further LLM calls. Experiments on article bodies, metadata, images, and tables show that PACE surpasses scalable non‑manual baselines and approaches the quality of manually engineered publisher‑specific parsers.
By Zhanlin Liu, Munirathnam Srikanth
arXiv:2504. 20114v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multiple document chunks.
By Zhonghao Li, Kunpeng Zhang, Jinghuai Ou, Shuliang Liu, Xuming Hu
arXiv:2607. 08269v1 Announce Type: new Abstract: Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML.
By Ying Liu, Yi Ye, Quanyu Feng, Mingxi Ye, Mingtao Zhang, Haoyang Li, Chen Jason Zhang, Qing Li
arXiv:2606. 28344v1 Announce Type: cross Abstract: Augmenting large language models (LLMs) with retrieved web text has become a dominant paradigm, yet the web is not natively textual: existing systems depend on complex parsing pipelines that linearize HTML and discard layout, visual structure, and formatting.
By Yichuan Wang, Zhifei Li, Zirui Wang, Paul Teiletche, Lesheng Jin, Matei Zaharia, Joseph E. Gonzalez, Sewon Min
arXiv:2602. 12187v2 Announce Type: replace-cross Abstract: Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to deliver synthesized answers.
By Sunghwan Kim, Wooseok Jeong, Serin Kim, Sangam Lee, Dongha Lee
WebArxiv is a reproducible benchmark designed to evaluate multimodal web agents on arXiv-related tasks. It consists of 510 static, time‑invariant tasks that require multi‑constraint paper retrieval, fine‑grained content extraction, and cross‑paper comparison, each with a deterministic ground truth. The benchmark highlights challenges for foundation‑model agents, such as over‑reliance on fixed interaction histories, and introduces a lightweight dynamic‑memory mechanism to improve adaptive retrieval and reasoning.
By Zihao Sun, Zijing Shi, Ling Chen