mlsanityData to 7 Oct 2026

Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach

arXiv 2407.13101 ↗First posted 18 Jul 2024cs.CL cs.AIcited by 40

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Multi-hop question answering is a challenging task with distinct industrial relevance, and Retrieval-Augmented Generation (RAG) methods based on large language models (LLMs) have become a popular approach to tackle this task. Owing to the potential inability to retrieve all necessary information in a single iteration, a series of iterative RAG methods has been recently developed, showing significant performance improvements. However, existing methods still face two critical challenges: context overload resulting from multiple rounds of retrieval, and over-planning and repetitive planning due to the lack of a recorded retrieval trajectory. In this paper, we propose a novel iterative RAG method called ReSP, equipped with a dual-function summarizer. This summarizer compresses information from retrieved documents, targeting both the overarching question and the current sub-question concurrently. Experimental results on the multi-hop question-answering datasets HotpotQA and 2WikiMultihopQA demonstrate that our method significantly outperforms the state-of-the-art, and exhibits excellent robustness concerning context length.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 26 of its 41 references that are in the map. First posted on arXiv 18 Jul 2024.

Builds on

26 of 41 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  2. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy24 May

Other references · 24

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  7. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  11. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
12 more
  1. 2023Active Retrieval Augmented Generationcited by 506
  2. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  3. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 165
  4. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 126
  5. 2023WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferencescited by 100
  6. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  7. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  8. 2022Multi-hop Question Answeringcited by 64
  9. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  10. 2024FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answeringcited by 18
  11. 2024Efficient Knowledge Infusion via KG-LLM Alignmentcited by 13
  12. 2023LMGQS: A Large-scale Dataset for Query-focused Summarizationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 26; 2026: 10.

40 papers.

Sort:

By area:

  1. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agentscited by 102
  2. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systemscited by 69
  3. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  4. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  5. 2024Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questionscited by 54
  6. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 49
  7. 2025PropRAG: Guiding Retrieval with Beam Search over Proposition Pathscited by 22
  8. 2025Supervising the search process produces reliable and generalizable information-seeking agentscited by 20
  9. 2025U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystackcited by 20
  10. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answeringcited by 12
  11. 2025LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searcherscited by 10
  12. 2026S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QAcited by 9
28 more
  1. 2025QAgent: A modular Search Agent with Interactive Query Understandingcited by 8
  2. 2026InfMem: Learning System-2 Memory Control for Long-Context Agentcited by 8
  3. 2025Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Designcited by 6
  4. 2026JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAGcited by 6
  5. 2025GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learningcited by 4
  6. 2025BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answeringcited by 3
  7. 2025Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learningcited by 3
  8. 2025Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answeringcited by 3
  9. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answeringcited by 3
  10. 2025From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Developmentcited by 2
  11. 2024ENCO: Life-Cycle Management of Enterprise-Grade Copilotscited by 1
  12. 2025Continually Self-Improving Language Models for Bariatric Surgery Question--Answeringcited by 1
  13. 2025Small Encoders Can Rival Large Decoders in Detecting Groundednesscited by 1
  14. 2025Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generationcited by 1
  15. 2025HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 1
  16. 2025STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Modelscited by 1
  17. 2025Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAGcited by 1
  18. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answeringcited by 1
  19. 2025Iterative Tree Analysis for Medical Criticscited by 0
  20. 2025Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QAcited by 0
  21. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAGcited by 0
  22. 2025SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novelscited by 0
  23. 2026RAG without Forgetting: Continual Query-Infused Key Memorycited by 0
  24. 2026Computability of Agentic Systemscited by 0
  25. 2026LakeQuest: A Three-Domain Benchmark for Grounded Question Answering across Data Lakescited by 0
  26. 2026HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answeringcited by 0
  27. 2026Cross-Domain Hybrid OPD for Generalizable Search Agentscited by 0
  28. 2026A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
  2. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
  3. 2026DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
  4. 2026ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
  5. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  6. 2025Optimizing Multi-Hop Document Retrieval Through Intermediate Representations
  7. 2024Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability
  8. 2025Question Decomposition for Retrieval-Augmented Generation