mlsanityData to 14 Oct 2026

RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA

arXiv 2510.20505 ↗First posted 23 Oct 2025cs.CL cs.AIcited by 1

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against latency and token/tool budgets. This paper introduces RELOOP, a structure aware framework using Hierarchical Sequence (HSEQ) that (i) linearize documents, tables, and knowledge graphs into a reversible hierarchical sequence with lightweight structural tags, and (ii) perform structure-aware iteration to collect just-enough evidence before answer synthesis. A Head Agent provides guidance that leads retrieval, while an Iteration Agent selects and expands HSeq via structure-respecting actions (e.g., parent/child hops, table row/column neighbors, KG relations); Finally the head agent composes canonicalized evidence to genearte the final answer, with an optional refinement loop to resolve detected contradictions. Experiments on HotpotQA (text), HybridQA/TAT-QA (table+text), and MetaQA (KG) show consistent EM/F1 gains over strong single-pass, multi-hop, and agentic RAG baselines with high efficiency. Besides, RELOOP exhibits three key advantages: (1) a format-agnostic unification that enables a single policy to operate across text, tables, and KGs without per-dataset specialization; (2) guided, budget-aware iteration that reduces unnecessary hops, tool calls, and tokens while preserving accuracy; and (3) evidence canonicalization for reliable QA, improving answers consistency and auditability.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 32 of its 48 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

32 of 48 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning12 Jun
  2. 2025KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG13 Feb
  3. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  4. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation15 Jul
  5. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr

Other references · 26

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  5. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  6. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  7. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  8. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  9. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  10. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  11. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  12. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
14 more
  1. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  2. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  3. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  4. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  5. 2022Re2G: Retrieve, Rerank, Generatecited by 102
  6. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generationcited by 90
  7. 2023Self-Adaptive Large Language Model (LLM)-Based Multiagent Systemscited by 31
  8. 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generationcited by 31
  9. 2021MetaQA: Combining Expert Agents for Multi-Skill Question Answeringcited by 15
  10. 2024EconNLI: Evaluating Large Language Models on Economics Reasoningcited by 8
  11. 2024RAG-based Question Answering over Heterogeneous Data and Textcited by 7
  12. 2025Hybrid Graphs for Table-and-Text based Question Answering using LLMscited by 7
  13. 2024HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QAcited by 6
  14. 2024TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarizationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  2. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
  3. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  4. 2026S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
  5. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
  6. 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
  7. 2025REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
  8. 2025SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework