Agentic RAG

RAG: Retrieval-Augmented Generation

Agentic RAG studies systems where a language model actively searches, inspects evidence, and decides whether to retrieve again before answering, rather than relying on a single retrieval pass. Common approaches include query decomposition, tool-using or multi-agent workflows, graph and hierarchical retrieval, and reinforcement learning that rewards useful evidence gathering and efficient stopping. These methods are tested on multi-hop question answering, long and multimodal documents, and domain-specific tasks such as clinical, legal, and financial reasoning. A central challenge is balancing answer quality with retrieval cost and latency while ensuring that evidence is sufficient, faithfully used, and not undermined by errors that accumulate across steps.

Latest papers

246 papers24 papers in the last four weeks, up 14% on the four weeks before. 0.1% of all new papers.

Reasoner-Executor-Synthesizer: Scalable Agentic Architecture with Static O(1) Context Window
Mar 23, 2026Ivan DobrovolskyiAgentic RAG LLM Hallucination Mitigation
Walmart Global Tech, Sunnyvale, CA, USA
MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessment
Mar 21, 2026Jiajun Hou, Hexuan Deng, Wenxiang Jiao +4Agentic RAG Memory-Augmented Agents
The Chinese University of Hong Kong, Shenzhen, China · Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China · Zhongguancun Academy, Beijing, China +2
HCAG: Hierarchical Abstraction and Retrieval-Augmented Generation on Theoretical Repositories with LLMs
Mar 19, 2026Yusen Wu, Xiaotie DengRepository-Level Code Generation Retrieval-Augmented Generation
Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
Mar 15, 2026Auksarapak Kietkajornrit, Jad Tarifi, Nima AsgharbeygiLLM Planning LLM Reliability
Integral AI
EviAgent: Evidence-Driven Agent for Radiology Report Generation
Mar 14, 2026Tuoshi Qi, Shenshen Bu, Yingfei Xiang +1Radiology Report Generation Medical VLMs
School of Computer Science and Engineering, Sun Yat-sen University · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Sangfor Technologies, Shenzhen, Guangdong, China
APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
Mar 14, 2026Kun Chen, Qingchao Kong, Zhao Feifei +1Agentic RAG RL for RAG
University of Chinese Academy of Sciences · MAIS, Institute of Automation, Chinese Academy of Sciences · Wenge Technology Co., Ltd
Test-Time Strategies for More Efficient and Accurate Agentic RAG
Mar 12, 2026Brian Zhang, Deepti Guntur, Zhiyang Zuo +7Retrieval-Augmented Generation Agentic RAG
University of Massachusetts Amherst · Adobe Research
DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering
Mar 12, 2026Teng Lin, Yizhang Zhu, Zhengxuan Zhang +2Multi-Document QA Multi-Hop QA
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology
When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows
Mar 12, 2026Wenxian Yang, Hanzheng Qiu, Bangqun Zhang +5Workflow Automation LLM Agent Memory
Independent Researcher · National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China · Yue’erwan Internet Hospital Co., Ltd. +4
Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval
Mar 11, 2026Andrea Volpini, Elie Raad, Beatrice Gamba +1Structured RAG Retrieval-Augmented Generation
WordLift, Rome, Italy
Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents
Mar 10, 2026Jiangming Shu, Yuxiang Zhang, Ye Ma +2Retrieval-Augmented Reasoning Agentic RAG
School of Computer Science and Technology, Beijing Jiaotong University · Hithink Research
Explainable Innovation Engine: Dual-Tree Agent-RAG with Methods-as-Nodes and Verifiable Write-Back
Mar 10, 2026Renwei MengAgentic RAG Retrieval-Augmented Generation
Anhui University, Hefei, China
Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search
Mar 9, 2026Kyle McCleary, James GhawalyAgentic Search Agentic RAG
Division of Computer Science & Engineering, Louisiana State University, Baton Rouge, Louisiana, USA
Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
Mar 9, 2026Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh +7Question Answering LLM Grounding
Qatar Computing Research Institute, HBKU, Qatar
SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
Mar 9, 2026Yagiz Can Akay, Muhammed Yusuf Kartal, Esra Alparslan +2Multi-Document QA Retrieval-Augmented Generation
TOBB University of Economics and Technology · OSTIM Technical University
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
Mar 7, 2026Saroj Mishra, Suman Niroula, Umesh Yadav +3Agentic RAG RAG Robustness
University of North Dakota · Youngstown State University · University of Toledo +2
Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing
Mar 6, 2026Anmol Gulati, Sahil Sen, Waqar Sarguroh +1Agentic RAG Spreadsheet Automation
Commercial Technology and Innovation Office, PricewaterhouseCoopers, U.S.
Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering
Mar 6, 2026Mina Farajiamiri, Jeta Sopa, Saba Afza +9LLM Reliability LLM Agent Reliability
Lab for AI in Medicine, RWTH Aachen University, Aachen, Germany. · Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. · Department of Diagnostic and Interventional Radiology, TUM University Klinikum, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany. +6
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
Mar 4, 2026Zavier Ndum Ndum, Jian Tao, John Ford +2Agentic RAG Multimodal RAG
Department of Nuclear Engineering, Texas A&M University, College Station, TX, USA · College of Performance, Visualization and Fine Arts, Texas A&M University, College Station, TX, USA
Saarthi for AGI: Towards Domain-Specific General Intelligence for Formal Verification
Mar 3, 2026Aman Kumar, Deepak Narayan Gadde, Luu Danh Minh +3SystemVerilog Assertion Generation LLM Agent Verification
Infineon Technologies India Private Limited, India · Infineon Technologies Dresden AG & Co. KG, Germany · Infineon Technologies Vietnam Company Ltd., Vietnam
VoiceAgentRAG: Solving the RAG Latency Bottleneck in Real-Time Voice Agents Using Dual-Agent Architectures
Mar 2, 2026Jielin Qiu, Jianguo Zhang, Zixiang Chen +12Agentic RAG Conversational Agents
Salesforce AI Research
GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
Mar 2, 2026Yuchen Ying, Weiqi Jiang, Tongya Zheng +4LLM Reasoning with Graphs Agentic RAG
Zhejiang University, Hangzhou, China · Hangzhou City University, Hangzhou, China · Nanyang Technological University, Singapore, Singapore
Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models
Mar 1, 2026Yichao Wu, Penghao Liang, Yafei Xiang +5Agentic RAG LLM Routing
Northeastern University Boston, USA, 02115 · Independent Researcher Milpitas, USA, 95035 · Independent Researcher Austin, USA, 78613 +2
Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking
Feb 27, 2026Shuzhi Gong, Richard O. Sinnott, Jianzhong Qi +3Automated Fact-Checking Evidence Retrieval
The University of Melbourne, Melbourne, VIC, Australia · Data61, CSIRO, Sydney, NSW, Australia · MBZUAI, Abu Dhabi, UAE
Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
Feb 26, 2026Chris Samarinas, Haw-Shiuan Chang, Hamed ZamaniReinforcement Learning Process Reward Models
Center for Intelligent Information Retrieval University of Massachusetts Amherst Amherst, MA, United States
CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery
Feb 26, 2026Mengze Hong, Di Jiang, Chen Jason Zhang +5AI-Assisted Scientific Research Citation Verification
Hong Kong Polytechnic University, Hong Kong, China · Beijing University of Posts and Telecommunications, Beijing, China · Independent Researcher, Hong Kong, China +2
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
Feb 26, 2026Tianle Xia, Ming Xu, Lingxiang Hu +7RL for RAG Agentic RAG
Tencent
Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering
Feb 22, 2026Maryam Amirizaniani, Alireza Salemi, Hamed ZamaniQuestion Answering Retrieval-Augmented Generation
University of Washington Seattle, WA, USA · University of Massachusetts Amherst Amherst, MA, USA
AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG
Feb 22, 2026Qijie You, Wenkai Yu, Wentao ZhangMulti-Hop QA LLM Agent Evaluation
University of Science and Technology Beijing · 2Peking University · 3Zhongguancun Academy +1
Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI
Feb 20, 2026Marcel OsmondAI Agent Governance AI Governance
QMUL CCLS, London, UK.

Mar 23, 2026J/K move · Enter open · S save

Reasoner-Executor-Synthesizer: Scalable Agentic Architecture with Static O(1) Context Window

Ivan Dobrovolskyi

Walmart Global Tech, Sunnyvale, CA, USA

Agentic RAG LLM Hallucination Mitigation Retrieval-Augmented Generation LLM Agent Harnesses

Open paper AskPDF arXiv

Large Language Models (LLMs) deployed as autonomous agents commonly use Retrieval-Augmented Generation (RAG), feeding retrieved documents into the context window, which creates two problems: the risk of hallucination grows with context length, and token cost scales linearly with dataset size. We propose the Reasoner-Executor-Synthesizer (RES) architecture, a three-layer design that strictly separates intent parsing (Reasoner), deterministic data retrieval and aggregation (Executor), and narrative generation (Synthesizer). The Executor uses zero LLM tokens and passes only fixed-size statistical summaries to the Synthesizer. We formally prove that RES achieves O(1) token complexity with respect to dataset size, and validate this on ScholarSearch, a scholarly research assistant backed by the Crossref API (130M+ articles). Across 100 benchmark runs, RES achieves a mean token cost of 1,574 tokens regardless of whether the dataset contains 42,000 or 16.3 million articles. The architecture eliminates data hallucination by construction: the LLM never sees raw records. KEYWORDS LLM agents; agentic architecture; hallucination elimination; token optimization; context window; retrieval-augmented generation; deterministic execution; scholarly metadata; Crossref API; O(1) complexity.