mlsanityData to 14 Oct 2026

Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering

arXiv 2601.11255 ↗First posted 16 Jan 2026cs.CL cs.LGcited by 14

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

also in 1 more
Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has demonstrated significant effectiveness in enhancing large language models (LLMs) for complex multi-hop question answering (QA). For multi-hop QA tasks, current iterative approaches predominantly rely on LLMs to self-guide and plan multi-step exploration paths during retrieval, leading to substantial challenges in maintaining reasoning coherence across steps from inaccurate query decomposition and error propagation. To address these issues, we introduce Reasoning Tree Guided RAG (RT-RAG), a novel hierarchical framework for complex multi-hop QA. RT-RAG systematically decomposes multi-hop questions into explicit reasoning trees, minimizing inaccurate decomposition through structured entity analysis and consensus-based tree selection that clearly separates core queries, known entities, and unknown entities. Subsequently, a bottom-up traversal strategy employs iterative query rewriting and refinement to collect high-quality evidence, thereby mitigating error propagation. Comprehensive experiments show that RT-RAG substantially outperforms state-of-the-art methods by 7.0% F1 and 6.0% EM, demonstrating the effectiveness of RT-RAG in complex multi-hop QA.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 28 of its 53 references that are in the map. First posted on arXiv 16 Jan 2026.

Builds on

28 of 53 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search26 Mar
  2. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Models3 Feb
  3. 2025Chain-of-Retrieval Augmented Generation24 Jan
  4. 2024SiReRAG: Indexing Similar and Related Information for Multihop Reasoning9 Dec
  5. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking31 Oct
  6. 2024Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation28 Oct

Other references · 22

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 379
  4. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 376
  5. 2024Corrective Retrieval Augmented Generationcited by 197
  6. 2022A Survey on Retrieval-Augmented Text Generationcited by 158
  7. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  8. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  9. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  10. 2024Why Does the Effective Context Length of LLMs Fall Short?cited by 63
  11. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  12. 2024From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debuggingcited by 46
10 more
  1. 2025LongCodeZip: Compress Long Context for Code Language Modelscited by 39
  2. 2025SWE-QA: Can Language Models Answer Repository-level Code Questions?cited by 38
  3. 2025Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisalcited by 32
  4. 2025Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answeringcited by 22
  5. 2025AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generationcited by 19
  6. 2025EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translationcited by 19
  7. 2025LastingBench: Defend Benchmarks Against Knowledge Leakagecited by 14
  8. 2025FlowMalTrans: Unsupervised Binary Code Translation for Malware Detection Using Flow-Adapter Architecturecited by 10
  9. 2025Robust Preference Alignment via Directional Neighborhood Consensuscited by 2
  10. 2025Beyond Chat: a Framework for LLMs as Human-Centered Support Systemscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026SWE-Pruner: Self-Adaptive Context Pruning for Coding Agentscited by 44
  2. 2026Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysiscited by 21
  3. 2026Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understandingcited by 13
  4. 2026Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-offcited by 13
  5. 2026Improving the Completeness and Comparability of Segment Disclosures: A Large Language Model Approachcited by 6
  6. 2026SWE-Pruner Pro: The Coder LLM Already Knows What to Prunecited by 2
  7. 2026Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?cited by 1
  8. 2026BaziQA-Benchmark: Evaluating Symbolic and Temporally Compositional Reasoning in Large Language Modelscited by 0
  9. 2026LLM Reasoning Is Latent, Not the Chain of Thoughtcited by 0
  10. 2026Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Studycited by 0
  11. 2026Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoningcited by 0
  12. 2026ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphscited by 0
2 more
  1. 2026HyGRL: Adaptive Hybrid Graph Reasoning for Multi-Entity Questionscited by 0
  2. 2026PANINI-DR: Controlled Deep Research through Generative Semantic Workspacescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
  2. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answering
  3. 2026ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
  4. 2026D2F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation
  5. 2025ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering
  6. 2025REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
  7. 2024EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
  8. 2024Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering