mlsanityData to 14 Oct 2026

Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering

arXiv 2508.17330 ↗First posted 24 Aug 2025cs.CL cs.AIcited by 1

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

Abstract (arXiv)

This paper introduces Omne-R1, a novel approach designed to enhance multi-hop question answering capabilities on schema-free knowledge graphs by integrating advanced reasoning models. Our method employs a multi-stage training workflow, including two reinforcement learning phases and one supervised fine-tuning phase. We address the challenge of limited suitable knowledge graphs and QA data by constructing domain-independent knowledge graphs and auto-generating QA pairs. Experimental results show significant improvements in answering multi-hop questions, with notable performance gains on more complex 3+ hop questions. Our proposed training framework demonstrates strong generalization abilities across diverse knowledge domains.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 38 references that are in the map. First posted on arXiv 24 Aug 2025.

Builds on

24 of 38 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents21 May
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  3. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph17 Feb

Other references · 21

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  8. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  10. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  11. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wildcited by 511
  12. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Modelcited by 461
9 more
  1. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  2. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 286
  3. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyondcited by 175
  4. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 119
  5. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 68
  6. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 68
  7. 2023S2CTrans: Building a bridge from SPARQL to Cyphercited by 6
  8. 2025NLI4DB: A Systematic Review of Natural Language Interfaces for Databasescited by 5
  9. 2022GlobalWalk: Learning Global-aware Node Embeddings via Biased Samplingcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Modelscited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2026Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering
  2. 2025KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration
  3. 2026KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
  4. 2025BMGQ: A Bottom-up Method for Generating Complex Multi-hop Reasoning Questions from Semi-structured Data
  5. 2026Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering
  6. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
  7. 2026AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
  8. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph