mlsanityData to 14 Oct 2026

Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAG

arXiv 2510.19171 ↗First posted 22 Oct 2025cs.CLcited by 1

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

Abstract (arXiv)

Multi-hop retrieval-augmented generation (RAG) is a promising strategy for complex reasoning, yet existing iterative prompting approaches remain inefficient. They often regenerate predictable token sequences at every step and rely on stochastic stopping, leading to excessive token usage and unstable termination. We propose TSSS (Think Straight, Stop Smart), a structured multi-hop RAG framework designed for efficiency. TSSS introduces (i) a template-based reasoning that caches recurring prefixes and anchors sub-queries to the main question, reducing token generation cost while promoting stable reasoning, and (ii) a retriever-based terminator, which deterministically halts reasoning once additional sub-queries collapse into repetition. This separation of structured reasoning and termination control enables both faster inference and more reliable answers. On HotpotQA, 2WikiMultiHop, and MuSiQue, TSSS achieves state-of-the-art accuracy and competitive efficiency among RAG-CoT approaches, highlighting its effectiveness in efficiency-constrained scenarios such as on-device inference.

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 22 of its 22 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

22 of 22 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering30 May
  2. 2024EfficientRAG: Efficient Retriever for Multi-Hop Question Answering8 Aug
  3. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach18 Jul
  4. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy24 May

Other references · 18

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2025Gemma 3 Technical Reportcited by 1,824
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  7. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  10. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  11. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  12. 2024Phi-4 Technical Reportcited by 711
6 more
  1. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  2. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  3. 2025Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn'tcited by 74
  4. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  5. 2024Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inferencecited by 7
  6. 2025Chain-of-Rank: Enhancing Large Language Models for Domain-Specific RAG in Edge Devicecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Feedback Adaptation for Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation
  2. 2026Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
  3. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answering
  4. 2025Investigating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries
  5. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  6. 2026Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
  7. 2025REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
  8. 2026Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS