Saved in:
Bibliographic Details
Main Authors: Luo, Jinchang, Cheng, Mingquan, Wan, Fan, Li, Ni, Xia, Xiaoling, Tian, Shuangshuang, Bian, Tingcheng, Wang, Haiwei, Fu, Haohuan, Tao, Yan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.20548
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917343628623872
author Luo, Jinchang
Cheng, Mingquan
Wan, Fan
Li, Ni
Xia, Xiaoling
Tian, Shuangshuang
Bian, Tingcheng
Wang, Haiwei
Fu, Haohuan
Tao, Yan
author_facet Luo, Jinchang
Cheng, Mingquan
Wan, Fan
Li, Ni
Xia, Xiaoling
Tian, Shuangshuang
Bian, Tingcheng
Wang, Haiwei
Fu, Haohuan
Tao, Yan
contents Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global planning absence to structure multi-step reasoning, and (ii) unfaithful execution, which hinders effective query formulation and consistent use of retrieved evidence. We propose GlobalRAG, a reinforcement learning framework designed to enhance global reasoning in multi-hop QA. GlobalRAG decomposes questions into subgoals, coordinates retrieval with reasoning, and refines evidence iteratively. To guide this process, we introduce Planning Quality Reward and SubGoal Completion Reward, which encourage coherent planning and reliable subgoal execution. In addition, a progressive weight annealing strategy balances process-oriented and outcome-based objectives. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that GlobalRAG significantly outperforms strong baselines while using only 8k training data (42% of the training data used by strong baselines), achieving average improvements of 14.2% in both EM and F1.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20548
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
Luo, Jinchang
Cheng, Mingquan
Wan, Fan
Li, Ni
Xia, Xiaoling
Tian, Shuangshuang
Bian, Tingcheng
Wang, Haiwei
Fu, Haohuan
Tao, Yan
Computation and Language
Artificial Intelligence
Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global planning absence to structure multi-step reasoning, and (ii) unfaithful execution, which hinders effective query formulation and consistent use of retrieved evidence. We propose GlobalRAG, a reinforcement learning framework designed to enhance global reasoning in multi-hop QA. GlobalRAG decomposes questions into subgoals, coordinates retrieval with reasoning, and refines evidence iteratively. To guide this process, we introduce Planning Quality Reward and SubGoal Completion Reward, which encourage coherent planning and reliable subgoal execution. In addition, a progressive weight annealing strategy balances process-oriented and outcome-based objectives. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that GlobalRAG significantly outperforms strong baselines while using only 8k training data (42% of the training data used by strong baselines), achieving average improvements of 14.2% in both EM and F1.
title GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.20548