# GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.20548 · HTML: https://mlsanity.com/paper/2510.20548/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 26 of 26)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024)
- [Understanding Dataset Design Choices for Multi-hop Reasoning](https://mlsanity.com/paper/1904.12106/) (2019)
- [ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents](https://mlsanity.com/paper/2508.14040/) (2025)
- [RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback](https://mlsanity.com/paper/2403.06840/) (2024)
- [Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach](https://mlsanity.com/paper/2407.13101/) (2024)
- [Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2505.11277/) (2025)
- [ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning](https://mlsanity.com/paper/2508.09303/) (2025)
- [Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning](https://mlsanity.com/paper/2311.03734/) (2023)
- [Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering](https://mlsanity.com/paper/2502.14245/) (2025)
- [DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2504.18243/) (2025)
- [GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning](https://mlsanity.com/paper/2507.23581/) (2025)
- [PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning](https://mlsanity.com/paper/2508.00344/) (2025)
- [LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization](https://mlsanity.com/paper/2505.17447/) (2025)
- [From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs](https://mlsanity.com/paper/2507.22716/) (2025)

## Built on by (most cited first, 5 of 5)

- [From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search](https://mlsanity.com/paper/2607.24280/) (2026)
- [D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2601.08282/) (2026)
- [When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering](https://mlsanity.com/paper/2601.19827/) (2026)
- [SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval](https://mlsanity.com/paper/2604.07415/) (2026)
- [Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination](https://mlsanity.com/paper/2610.05382/) (2026)

## Abstract (arXiv)

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.