mlsanityData to 14 Oct 2026

Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval

arXiv 2606.05658 ↗First posted 4 Jun 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding their responses in external knowledge, but conventional pipelines rely on static, single-step retrieval that limits performance on complex queries. This paper presents an Agent-Orchestrated Adaptive RAG framework that introduces dynamic query decomposition, iterative retrieval, and a bounded self-reflective evaluation loop. We evaluate the system across two complementary datasets: a domain-specific DevOps knowledge base and the multi-hop reasoning benchmark MuSiQue. Using metrics that include overall score, citation accuracy, mean reciprocal rank, and topic coverage, we find that query decomposition yields consistent gains in the structured domain (overall score +0.04, MRR +0.17 on DevOps) but degrades ranking precision on the multi-hop benchmark, while the reflection mechanism improves citation accuracy at a substantial latency cost. These contrasting results show that agentic enhancements are not universally beneficial and must be applied selectively according to query and domain characteristics. Our findings argue for adaptive, cost-aware orchestration rather than uniformly aggressive reasoning pipelines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 32 of its 49 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

32 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions7 Mar
  2. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG15 Jan

Other references · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  10. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  11. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  12. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
18 more
  1. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  4. 2017Billion-scale similarity search with GPUscited by 2,497
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  10. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  11. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  12. 2018Self-Attention with Relative Position Representationscited by 1,120
  13. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  14. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  15. 2024Corrective Retrieval Augmented Generationcited by 197
  16. 2023Query2doc: Query Expansion with Large Language Modelscited by 149
  17. 2025Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversioncited by 63
  18. 2026Chunking, Retrieval, and Re-ranking: An Empirical Evaluation of RAG Architectures for Policy Document Question Answeringcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  2. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
  3. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  4. 2025FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation
  5. 2026Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering
  6. 2025SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework
  7. 2026AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG
  8. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation