mlsanityData to 7 Oct 2026

Agentic RAG, agents and memory

449 papers2 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: reasoning, rag, retrieval, retrieval-augmented, agentic

Key facts. Agentic RAG, agents and memory: 449 papers on arXiv since 2022 (data through 7 Oct 2026). 47 of its 449 mapped papers (10%) cite “Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG” (2025, arXiv 2501.09136). 12 of its 449 mapped papers (3%) cite “RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement” (2024, arXiv 2412.12881). 15 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

15 new papers, 17 Sep – 7 Oct; 2 this week.

  1. This week · 2
  2. The Attribution Blind Spot: Layerwise Trajectory Diagnostics for Source Reliance in Retrieval-Augmented Language Models also fits: RAG robustness and adaptive retrieval
  3. Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
  4. Earlier · 13
  5. Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads also fits: RAG robustness and adaptive retrieval
  6. Retrieval-Augmented Large Language Model Decision-Making for Autonomous Driving Guided by Chinese Philosophical Wisdom
  7. Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation also fits: RAG robustness and adaptive retrieval
  8. On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI Tutor also fits: RAG pipeline design and evaluation
  9. Conversational Capture: A Trajectory-Level Framework for Evaluating Generative Engine Optimization in Multi-turn Human-Agent Interaction also fits: Conversational and speech RAG
  10. Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
  11. RAGWarrant: Evidence-Preserving Governance for RAG Policy Promotion Under Quality, Cost, Latency, and Risk Constraints also fits: Legal and financial RAG
  12. The Fellowship of the Query: Learning Retrieval Actions also fits: Generation and context integration
All 15
  1. Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents
  2. From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework
  3. Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison also fits: RAG robustness and adaptive retrieval
  4. Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents
  5. RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents also fits: Legal and financial RAG

Foundations

Most cited by papers here

  1. Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG2025cited by 47 here
  2. RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement2024cited by 12 here
  3. Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning2025cited by 12 here
  4. PaperQA: Retrieval-Augmented Generative Agent for Scientific Research2023cited by 9 here
  5. RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation2024cited by 8 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 53 here
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 299 here
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 40 here
  4. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 30 here
  5. 2023In-Context Retrieval-Augmented Language Modelscited by 24 here
  6. 2023Active Retrieval Augmented Generationcited by 35 here
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 127 here
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 86 here
  9. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 13 here
  10. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 24 here
14 more it builds on, not in this chain
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 51 here
  2. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 13 here
  3. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 40 here
  4. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 19 here
  5. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 15 here
  6. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 16 here
  7. 2024Corrective Retrieval Augmented Generationcited by 14 here
  8. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 25 here
  9. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 55 here
  10. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 15 here
  11. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 43 here
  12. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 18 here
  13. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makerscited by 12 here
  14. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 47 here

The 24 most cited of 632.

Browse

30 of 449, ranked 6–35

  1. 6ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding20258
  2. 7s3: You Don't Need That Much Data to Train a Search Agent via RL20258
  3. 8MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning20257
  4. 9MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation20247
  5. 10A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces20266
  6. 11DeepRAG: Thinking to Retrieve Step by Step for Large Language Models20256
  7. 12Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning20256
  8. 13RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents20246
  9. 14LeanDojo: Theorem Proving with Retrieval-Augmented Language Models20236
  10. 15Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty20255
All 30
  1. 16RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards20245
  2. 17Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning20254
  3. 18Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent20254
  4. 19Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning20254
  5. 20SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis20254
  6. 21R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning20254
  7. 22R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning20254
  8. 23Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs20254
  9. 24From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs20254
  10. 25HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation20254
  11. 26ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator20244
  12. 27Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training20263
  13. 28Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning20253
  14. 29RARE: Retrieval-Augmented Reasoning Modeling20253
  15. 30HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation20253
  16. 31A Survey of Personalization: From RAG to Agent20253
  17. 32Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging20253
  18. 33Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges20253
  19. 34OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval20253
  20. 35DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision20253