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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Boyuan, Ji, Feng, Nan, Jiayan, Zhao, Han, Chen, Weiling, Xu, Shihao, Zhou, Xing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914002213273600
author Liu, Boyuan
Ji, Feng
Nan, Jiayan
Zhao, Han
Chen, Weiling
Xu, Shihao
Zhou, Xing
author_facet Liu, Boyuan
Ji, Feng
Nan, Jiayan
Zhao, Han
Chen, Weiling
Xu, Shihao
Zhou, Xing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17330
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering
Liu, Boyuan
Ji, Feng
Nan, Jiayan
Zhao, Han
Chen, Weiling
Xu, Shihao
Zhou, Xing
Computation and Language
Artificial Intelligence
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.
title Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.17330