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

Source: [Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering](<https://www.sota2.com/research/paper/68fa7ae21e209131cea85a89>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:20.825Z

Authors: Boyuan Liu, Feng Ji, Jiayan Nan, Han Zhao, Weiling Chen, Shihao Xu, Xing Zhou

Published: 2025-08-24T12:36:48.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.17330>)

[PDF](<https://arxiv.org/pdf/2508.17330.pdf>)