Lune

ACL Findings2025

GeAR: Graph-enhanced Agent for Retrieval-augmented Generation

Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Enting Chen, Damien Graux, André Melo, Ruofei Lai, Zeren Jiang, Zhongyang Li, Ye Qi

Abstract

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 stateof-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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

9 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • G^2-Reader: Dual Evolving Graphs for Multimodal Document QA cites Active Retrieval Augmented Generation
  • HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
  • HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
  • HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models cites Active Retrieval Augmented Generation
  • Active Retrieval Augmented Generation cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers9

  1. MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning ChainsXuying Ning, Dongqi Fu, Tianxin Wei, Mengting Ai et al.ICLR 2026 · 14 citations
  2. FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge FlowYusong Hu, Runmin Ma, Yue Fan, Jinxin Shi et al.ACL 2026 · 9 citations
  3. G2G^2-Reader: Dual Evolving Graphs for Multimodal Document QAYaxin Du, Junru Song, Yifan Zhou, Cheng Wang et al.ICML 2026 · 1 citation
  4. From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal JungleKaustubh Vyas, Damien Graux, Yijun Yang, Sébastien Montella et al.ICLR 2025
  5. MaDS: Long-Horizon GUI Automation via Synergizing Dual-Layer Memory and Multi-Round DebatePengchen Chen, Shi Chen, Qiming Ye, Xinli Chen et al.ACL 2026

Builds on12

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  2. RAPTOR: Recursive Abstractive Processing for Tree-Organized RetrievalParth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna et al.ICLR 2024 · 460 citations
  3. HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsBernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga et al.NeurIPS 2024 · 395 citations
  4. LongRoPE: Extending LLM Context Window Beyond 2 Million TokensYiran Ding, Li Lyna Zhang, Chengruidong Zhang, Yuanyuan Xu et al.ICML 2024 · 316 citations
  5. Active Retrieval Augmented GenerationZhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun et al.EMNLP 2023 · 315 citations

Related papers

  1. Optimizing Multi-Hop Document Retrieval Through Intermediate RepresentationsLinjiaen Linjiaen, Jingyu Liu, Yingbo LiuACL Findings 2025 · 1 citation
  2. Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question AnsweringRongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang et al.ACL 2025 · 14 citations
  3. CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question AnsweringHao Yang, Zhiyu Yang, Xupeng Zhang, Wei Wei et al.WWW 2026
  4. TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented GenerationJinyuan Fang, Zaiqiao Meng, Craig MacDonaldEMNLP Findings 2024 · 23 citations
  5. SiReRAG: Indexing Similar and Related Information for Multihop ReasoningNan Zhang, Prafulla Kumar Choubey, Alexander R. Fabbri, Gabriel Bernadett-Shapiro et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines