mlsanityData to 7 Oct 2026

Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends

arXiv 2601.00536 ↗First posted 2 Jan 2026cs.CLcited by 8

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Multi-hop question answering (QA) requires systems to iteratively retrieve evidence and reason across multiple hops. While recent RAG and agentic methods report strong results, the underlying retrieval--reasoning process is often left implicit, making procedural choices hard to compare across model families. This survey takes the execution procedure as the unit of analysis and introduces a four-axis framework covering (A) overall execution plan, (B) index structure, (C) next-step control (strategies and triggers), and (D) stop/continue criteria. Using this schema, we map representative multi-hop QA systems and synthesize reported ablations and tendencies on standard benchmarks (e.g., HotpotQA, 2WikiMultiHopQA, MuSiQue), highlighting recurring trade-offs among effectiveness, efficiency, and evidence faithfulness. We conclude with open challenges for retrieval--reasoning agents, including structure-aware planning, transferable control policies, and robust stopping under distribution shift.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 26 of its 79 references that are in the map. First posted on arXiv 2 Jan 2026.

Builds on

26 of 79 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration12 Aug
  2. 2025Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?10 Mar
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  4. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph2 Dec

Other references · 22

  1. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  2. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  3. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  4. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  5. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  6. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  7. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  8. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 238
  9. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  10. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  11. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  12. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
10 more
  1. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  2. 2024MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Timecited by 40
  3. 2024FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Modelscited by 29
  4. 2024Long Context vs. RAG for LLMs: An Evaluation and Revisitscited by 24
  5. 2025Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMAcited by 23
  6. 2025Stop-RAG: Value-Based Retrieval Control for Iterative RAGcited by 13
  7. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answeringcited by 12
  8. 2025Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinkingcited by 9
  9. 2025CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inferencecited by 7
  10. 2025Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signalscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026RAM: Recover Any 3D Human Motion in-the-Wildcited by 11
  2. 2026Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Auditcited by 8
  3. 2026Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memorycited by 6
  4. 2026Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptationcited by 1
  5. 2026BCL: Bayesian In-Context Learning Framework for Information Extractioncited by 1
  6. 2026Auditing the Audit: Five Failure Modes in Benchmark-Validity Auditscited by 1
  7. 2026Where Privacy Risk Lives in English-Source Multilingual RAG: A Stage-Decomposed Audit Across Five Query Languagescited by 0
  8. 2026Exploratory As-Analyzed No-Detection of Culturally-Marked Predicate-Triggered PII Amplification in a Synthetic-English RAG Probe: A Predicate-Resource-Confounded Auditcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
  2. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
  3. 2026PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
  4. 2025BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering
  5. 2026STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering
  6. 2024Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
  7. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
  8. 2026PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering