# GeAR: Graph-enhanced Agent for Retrieval-augmented Generation

arXiv: https://arxiv.org/abs/2412.18431 · HTML: https://mlsanity.com/paper/2412.18431/

## Key facts

- Cited by 17 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 32 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## 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)
- [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)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens](https://mlsanity.com/paper/2402.13753/) (2024)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Knowledge Graph Prompting for Multi-Document Question Answering](https://mlsanity.com/paper/2308.11730/) (2023)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [Comparison of Diverse Decoding Methods from Conditional Language Models](https://mlsanity.com/paper/1906.06362/) (2019)
- [KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation](https://mlsanity.com/paper/2409.13731/) (2024)
- [GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models](https://mlsanity.com/paper/2406.14550/) (2024)
- [TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.11460/) (2024)
- [Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning](https://mlsanity.com/paper/2407.03227/) (2024)

## Built on by (most cited first, 17 of 17)

- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale](https://mlsanity.com/paper/2606.03056/) (2026)
- [MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains](https://mlsanity.com/paper/2603.00873/) (2026)
- [FlowSearch: Advancing deep research with dynamic structured knowledge flow](https://mlsanity.com/paper/2510.08521/) (2025)
- [Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking](https://mlsanity.com/paper/2508.02435/) (2025)
- [BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering](https://mlsanity.com/paper/2505.11811/) (2025)
- [HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores](https://mlsanity.com/paper/2509.21336/) (2025)
- [GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.22009/) (2025)
- [Decomposing and Revising What Language Models Generate](https://mlsanity.com/paper/2509.00765/) (2025)
- [MARC: Multimodal and Multi-Task Agentic Retrieval-Augmented Generation for Cold-Start Recommender System](https://mlsanity.com/paper/2511.08181/) (2025)
- [G2-Reader: Dual Evolving Graphs for Multimodal Document QA](https://mlsanity.com/paper/2601.22055/) (2026)
- [VLM-DEWM: Dynamic External World Model for Verifiable and Resilient Vision-Language Planning in Manufacturing](https://mlsanity.com/paper/2602.15549/) (2026)
- [GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework](https://mlsanity.com/paper/2509.00449/) (2025)
- [EviReform: Evidence-Guided Query Reformulation for Multi-Hop Graph Retrieval](https://mlsanity.com/paper/2608.13006/) (2026)
- [Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction](https://mlsanity.com/paper/2609.06391/) (2026)
- [Beyond Similarity through Zero-Token Geometric Graphs for Multi-Hop RAG](https://mlsanity.com/paper/2609.19622/) (2026)

## Abstract (arXiv)

Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers inherently struggle with multi-hop retrieval scenarios. In this paper, we introduce GeAR, a system that advances RAG performance through two key innovations: (i) an efficient graph expansion mechanism that augments any conventional base retriever, such as BM25, and (ii) an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework. Our evaluation demonstrates GeAR's superior retrieval capabilities across three multi-hop question answering datasets. Notably, our system achieves state-of-the-art results with improvements exceeding 10% on the challenging MuSiQue dataset, while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems. The project page is available at https://gear-rag.github.io.