{"ID":2878899,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17330","arxiv_id":"2508.17330","title":"Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2508.17330","url_pdf":"https://arxiv.org/pdf/2508.17330v1","authors":"[\"Boyuan Liu\",\"Feng Ji\",\"Jiayan Nan\",\"Han Zhao\",\"Weiling Chen\",\"Shihao Xu\",\"Xing Zhou\"]","published":"2025-08-24T12:36:48Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}