DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (CAS)（人工智能安全国家重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences, CAS（中国科学院大学）；Wenlan School of Business, Zhongnan University of Economics（中南财经政法大学文澜商学院）
Zhanli Li, Huiwen Tian, Lvzhou Luo, Yixuan Cao, Ping Luo
备注：
This version has significantly enhanced the clarity of our research
With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing agentic search frameworks typically treat long documents as flat collections of unstructured chunks, disregarding the native hierarchical organization and sequential logic essential for human comprehension. To bridge this gap, we introduce \textbf{DeepRead}, a structure-aware document reasoning agent designed to operationalize document-native structural priors into actionable reasoning capabilities. Leveraging the structural fidelity of modern OCR, DeepRead constructs a paragraph-level, coordinate-based navigation system and equips the LLM with two synergistic tools: \textsf{Retrieve} for scanning-aware localization, and \textsf{ReadSection} for contiguous, order-preserving reading within specific hierarchical scopes. This design elicits a human-like ``locate-then-read'' reasoning paradigm, effectively mitigating the context fragmentation inherent in traditional retrieval methods. Extensive evaluations across four benchmarks spanning diverse document types demonstrate that DeepRead outperforms Search-o1-style agentic search baselines by an average of 10.3\%. Fine-grained behavioral analysis further confirms that DeepRead autonomously adopts human-aligned reading strategies, validating the critical role of structural awareness in achieving precise document reasoning. Our code is available at https://github.com/Zhanli-Li/DeepRead.
Recent advancements in the area of Computer Vision with state-of-art Neural Networks has given a boost to Optical Character Recognition (OCR) accuracies. However, extracting characters/text alone is often insufficient for relevant information extraction as documents also have a visual structure that is not captured by OCR. Extracting information from tables, charts, footnotes, boxes, headings and retrieving the corresponding structured representation for the document remains a challenge and finds application in a large number of real-world use cases. In this paper, we propose a novel enterpris…
Agentic AI Sustainability Assessment for Supply Chain Document Insights
Head of AI, Tesisquare（Tesisquare人工智能负责人）；Voiceinteroperability.ai Initiative Member（Voiceinteroperability.ai项目成员）；Linux Foundation AI & Data（Linux基金会人工智能与数据）；Functional Analyst, Tesisquare（Tesisquare功能分析师）；MSc in Engineering Management Polytechnic University of Turin（理工学院工程管理硕士）；Assistant Professor in PM and Supply Chain Management Polytechnic University of Turin（理工学院项目管理与供应链管理副教授）
Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research
Infmedix, Co., Ltd.（Infmedix公司）；Department of Transdisciplinary Studies, Seoul National University（首尔国立大学跨学科研究系）；Healthcare AI Research Institute, Seoul National University Hospital（首尔国立大学医院医疗人工智能研究所）；Department of Medicine, Seoul National University College of Medicine（首尔国立大学医学院医学系）；Department of Transdisciplinary Medicine, Seoul National University Hospital（首尔国立大学医院跨学科医学系）；Department of Radiology, Massachusetts General Hospital and Harvard Medical School（麻省总医院放射科及哈佛医学院）
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
University of Cambridge（剑桥大学）；University of Washington（华盛顿大学）；Harvard Law School（哈佛法学院）；Stanford University（斯坦福大学）；Concordia AI（康科迪亚AI）；University of Pennsylvania（宾夕法尼亚大学）；Massachusetts Institute of Technology（麻省理工学院）；Hebrew University of Jerusalem（耶路撒冷希伯来大学）
Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development
Center for Proteomics and Metabolomics, Leiden University Medical Center（蛋白质组学与代谢组学中心，莱顿大学医学中心）；National Institute of Standards and Technology - Charleston（国家标准与技术研究院-查尔斯顿）
A Case for Agentic Tuning: From Documentation to Action in PostgreSQL
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Key Laboratory of System Software (Chinese Academy of Sciences)（中国科学院系统软件重点实验室）；Beihang University（北航）；Peking University（北京大学）；Shanghai Jiao Tong University（上海交通大学）
Question's Gambit: The First Move Matters in Agentic Deep Search
University of Toronto（多伦多大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；University of Waterloo（滑铁卢大学）；University of California, Berkeley（加州大学伯克利分校）；McGill University（麦吉尔大学）
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Cleveland State University（克利夫兰州立大学）；Kent State University（肯特州立大学）；Northeastern University（东北大学）；Roux Institute at Northeastern University（东北大学鲁克斯研究所）；University of Agder (UiA)（阿格德尔大学）
AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization
Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，地点，国家）；School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，地点，国家）；University of Delaware, Newark, DE, USA（特拉华大学）
DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning
Ant Group（蚂蚁集团）；Nanyang Technological University（南洋理工大学）；CFAR and IHPC, Agency for Science, Technology and Research (A*STAR), Singapore（新加坡科技研究局（A*STAR）计算与先进机器人中心及高性能计算研究所）
Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
Institute for Artificial Intelligence in Medicine (IKIM), University Medicine Essen（埃森大学医学院人工智能医学研究所）；Faculty of Computer Science, University of Duisburg-Essen（杜伊斯堡-埃森大学计算机科学学院）；Department of Physics, TU Dortmund University（多特蒙德工业大学物理系）；Lamarr Institute for Machine Learning and Artificial Intelligence, TU Dortmund University（多特蒙德工业大学拉马尔机器学习和人工智能研究所）；Advanced Clinical Research Center, Fukushima Medical University（福岛医科大学先进临床研究中心）；Department of Cardiology and Vascular Medicine, University Hospital Essen（埃森大学医院心血管内科）
DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice
Product Development Division, Department of Mechanical Engineering, Chalmers University of Technology, Gothenburg, Sweden（产品开发部门，机械工程系，楚姆勒斯技术大学，哥德堡，瑞典）；GKN Aerospace Engine Systems, Trollhättan, Sweden（GKN航空发动机系统，特罗尔哈塔纳，瑞典）
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
Department of Nuclear Engineering, Texas A\&M University, College Station, TX, USA；College of Performance, Visualization；Fine Arts, Texas A\&M University, College Station, TX, USA
