Agentic Retrieval

Ask about this topic

Overview

Agentic retrieval studies how AI agents find and use external information through successive search, inspection, and reasoning steps rather than relying on a single ranked result list. Common approaches combine lexical or dense search with query reformulation, document navigation, graphs or structured memory, and tools for checking evidence and deciding when to stop. The methods are tested in settings such as multi-hop question answering, deep research, long-term conversational memory, code repositories, and multimodal search, with training increasingly drawing on agent trajectories and reinforcement learning. Agents can improve evidence finding on complex tasks, but extra tool calls bring latency and cost, and better retrieval does not guarantee correct reasoning or faithful answers.

Latest papers

CardsList

97 papers13 papers in the last four weeks, up 18% on the four weeks before. 0.1% of all new papers.

  1. Behind the Prompt: The Agent-User Problem in Information Retrieval

    Mar 4, 2026Saber Zerhoudi, Michael Granitzer, Dang Hai Dang +5User ModelingAgentic Retrieval

    University of Passau, Passau, Germany · IT:U Austria, Linz, Austria

  2. Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis

    Feb 24, 2026Jason Liang, Elliot Meyerson, Risto MiikkulainenWeb AgentsDeep Research Agents

    Cognizant AI Lab · University of Texas at Austin

  3. Agentic Framework for Political Biography Extraction

    Feb 23, 2026Yifei Zhu, Songpo Yang, Jiangnan Zhu +1Document Information ExtractionLLM Information Extraction

    Ph.D candidate, Department of Politics and Public Administration, The University of Hong Kong. · Boya Postdoctoral Fellow, School of International Studies, Peking University. · Associate Professor, Department of Politics and Public Administration, The University of Hong Kong. +1

  4. TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning

    Feb 15, 2026Nicolas Zumarraga, Thomas Kaar, Ning Wang +12Time Series ReasoningTime Series QA

    1Agentic Systems Lab, ETH Zurich · 2Stanford University · 3Traffic Engineering Group, Institute for Transport Planning and Systems, ETH Zurich +4

  5. A-MapReduce: Executing Wide Search via Agentic MapReduce

    Feb 1, 2026Mingju Chen, Guibin Zhang, Heng Chang +2Multi-Agent LLM SystemsAgentic Retrieval

    Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University · National University of Singapore · Tsinghua University

  6. ShardMemo: Scope-Before-Routing for Agentic Memory Retrieval

    Jan 29, 2026Yang Zhao, Chengxiao Dai, Mengying Kou +2Agentic RetrievalInformation Retrieval

    Anonymous

  7. From Crawled to Published: A Publisher-Controlled Web Architecture for an AI-Native Internet

    Nov 23, 2025Yixi Chen, Muhammad Bilal, Tie Ma +3Information RetrievalAgentic Retrieval