CuSearch reallocates rollout budget in RLVR toward deeper-search trajectories as a proxy for retrieval supervision density, yielding up to 11.8 exact-match gains over uniform GRPO sampling on ZeroSearch.
hub Canonical reference
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Canonical reference. 91% of citing Pith papers cite this work as background.
48
Pith papers citing it
Background
91% of classified citations
abstract
Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real-time queries, resulting in outdated or inaccurate outputs. Retrieval-Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by integrating real-time data retrieval to provide contextually relevant and up-to-date responses. Despite its promise, traditional RAG systems are constrained by static workflows and lack the adaptability required for multi-step reasoning and complex task management. Agentic Retrieval-Augmented Generation (Agentic RAG) transcends these limitations by embedding autonomous AI agents into the RAG pipeline. These agents leverage agentic design patterns reflection, planning, tool use, and multi-agent collaboration to dynamically manage retrieval strategies, iteratively refine contextual understanding, and adapt workflows through operational structures ranging from sequential steps to adaptive collaboration. This integration enables Agentic RAG systems to deliver flexibility, scalability, and context-awareness across diverse applications. This paper presents an analytical survey of Agentic RAG systems. It traces the evolution of RAG paradigms, introduces a principled taxonomy of Agentic RAG architectures based on agent cardinality, control structure, autonomy, and knowledge representation, and provides a comparative analysis of design trade-offs across existing frameworks. The survey examines applications in healthcare, finance, education, and enterprise document processing, and distills practical lessons for system designers and practitioners. Finally, it identifies key open research challenges related to evaluation, coordination, memory management, efficiency, and governance, outlining directions for future research.
hub tools
citation-role summary
background 11
citation-polarity summary
roles
background 11representative citing papers
LatentRAG performs agentic RAG by generating latent tokens for thoughts and subqueries in one forward pass, matching explicit methods' accuracy on seven benchmarks while reducing latency by ~90%.
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
A-MAR decomposes art queries into reasoning plans to condition retrieval, leading to improved explanation quality and multi-step reasoning on art benchmarks compared to baselines.
Corpus2Skill converts document corpora into navigable hierarchical skill directories for LLM agents, improving QA and RAG quality on single-domain enterprise data but not on open-domain or tabular corpora.
E2E-REME outperforms nine LLMs in accuracy and efficiency for end-to-end microservice remediation by using experience-simulation reinforcement fine-tuning on a new benchmark called MicroRemed.
DotRAG reformulates graph retrieval as query-guided path reasoning with Division of Thought, reporting SOTA results on MetaQA and UltraDomain for multi-hop tasks.
Q-RAG trains embedders via RL for multi-step retrieval and reports state-of-the-art results on BabiLong and RULER benchmarks for contexts up to 10M tokens.
HiPRAG adds hierarchical process rewards to RL training for agentic RAG, reducing over-search to 2.3% and achieving 65.4-67.2% accuracy on seven QA benchmarks across 3B and 7B models.
MedEvoEval is an executable longitudinal evaluation framework that converts medical cases into action-gated simulated episodes to track how doctor agents evolve decision-making, resource use, and experience across multiple encounters.
GDP-RAG targets only information deltas in multi-hop RAG through preliminary grounding, gap-conditioned prompts, and skeletal trajectories, reaching 60.63% accuracy at 0.51 cost-of-pass on HotpotQA, 2WikiMultiHopQA, and MuSiQue.
DualGraph combines semantic textual KGs with symbolic KGs for semi-structured QA and introduces the SpecsQA benchmark, outperforming baselines on both open and specification questions.
EfficientGraph-RAG structures retrieval state with TAM, MARS and SMP, ranking first on averaged LongBench answer-quality metrics while cutting token use 3.51x on HotpotQA.
Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
FinAgent-RAG achieves 76.81-78.46% execution accuracy on financial QA benchmarks by combining contrastive retrieval, program-of-thought code generation, and adaptive strategy routing, outperforming baselines by 5.62-9.32 points.
Metadata Reasoner uses agentic LLM reasoning on metadata to select sufficient and minimal data sources, achieving 83.16% F1 on KramaBench and 85.5% F1 on noisy synthetic benchmarks while avoiding low-quality tables 99% of the time.
Agentic GraphRAG constructs a Neo4j graph via deterministic structured ingestion plus LLM extraction from notices, then deploys modular agents with tool access and reflection to outperform vector-RAG baselines on Swiss commercial gazette data across entity resolution, answer quality, and multi-turn
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
KbSD uses a same-size hint-augmented teacher and quadrant-adaptive KL objectives to deliver dense supervision for calibrated behavior across knowledge states in agentic search.
DynaTree separates offline agentic tree construction from online subtree selection to deliver better recall, ranking, and production survival rates than standard or prior agentic RAG for news retrieval.
VikingMem implements the Memory Base paradigm via event-centric extraction and entity updates on VikingDB with temporal compression, claiming up to 30% better retrieval effectiveness on long-term memory benchmarks.
AIBuildAI-2 introduces a knowledge-enhanced agent with a hierarchical evolving external knowledge base that dynamically loads relevant AI development expertise, achieving first place on MLE-Bench at 70.7% medal rate.