# SUBQRAG: Sub-Question Driven Dynamic Graph RAG

arXiv: https://arxiv.org/abs/2510.07718 · HTML: https://mlsanity.com/paper/2510.07718/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 16 of its 17 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [EfficientRAG: Efficient Retriever for Multi-Hop Question Answering](https://mlsanity.com/paper/2408.04259/) (2024)
- [Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion](https://mlsanity.com/paper/1909.11359/) (2019)
- [Credible Plan-Driven RAG Method for Multi-Hop Question Answering](https://mlsanity.com/paper/2504.16787/) (2025)
- [Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs](https://mlsanity.com/paper/2506.19967/) (2025)

## Built on by (most cited first, 3 of 3)

- [Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering](https://mlsanity.com/paper/2607.23278/) (2026)
- [D2F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation](https://mlsanity.com/paper/2608.04444/) (2026)
- [LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding](https://mlsanity.com/paper/2608.16004/) (2026)

## Abstract (arXiv)

Graph Retrieval-Augmented Generation (Graph RAG) effectively builds a knowledge graph (KG) to connect disparate facts across a large document corpus. However, this broad-view approach often lacks the deep structured reasoning needed for complex multi-hop question answering (QA), leading to incomplete evidence and error accumulation. To address these limitations, we propose SubQRAG, a sub-question-driven framework that enhances reasoning depth. SubQRAG decomposes a complex question into an ordered chain of verifiable sub-questions. For each sub-question, it retrieves relevant triples from the graph. When the existing graph is insufficient, the system dynamically expands it by extracting new triples from source documents in real time. All triples used in the reasoning process are aggregated into a "graph memory," forming a structured and traceable evidence path for final answer generation. Experiments on three multi-hop QA benchmarks demonstrate that SubQRAG achieves consistent and significant improvements, especially in Exact Match scores.