pith. sign in

arxiv: 2606.00610 · v1 · pith:N4DI56SHnew · submitted 2026-05-30 · 💻 cs.IR · cs.AI· cs.MA

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

Chuanjie Wu , Zhishang Xiang , Yunbo Tang , Zerui Chen , Qinggang Zhang , Jinsong Su This is my paper

Pith reviewed 2026-06-28 18:18 UTC · model grok-4.3

classification 💻 cs.IR cs.AIcs.MA
keywords MemGraphRAGGraphRAGmulti-agent systemshared memoryknowledge graphretrieval-augmented generationRAGgraph construction
0
0 comments X

The pith

MemGraphRAG uses a shared-memory multi-agent system to build consistent and connected knowledge graphs for improved retrieval-augmented generation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tries to establish that isolated fragment-level graph extraction leads to poor quality graphs in GraphRAG. It proposes using a collaborative society of agents with shared memory to give every agent a global view of the corpus. This shared context lets the agents resolve logical conflicts and keep the graph structurally connected as they extract information. Experiments on benchmarks show this method beats existing baselines while using similar computational resources.

Core claim

MemGraphRAG introduces a memory-based multi-agent system in which a collaborative society of agents, supported by shared memory that supplies unified global context, dynamically resolves logical conflicts and maintains structural connectivity during graph construction from large unstructured corpora.

What carries the argument

The shared memory that provides a unified global context to the society of agents throughout the extraction process, enabling conflict resolution and connectivity maintenance.

If this is right

  • Graphs produced are thematically consistent without logical conflicts.
  • Structural connectivity is preserved across the entire corpus.
  • Memory-aware hierarchical retrieval can leverage the improved graph structure.
  • Retrieval performance on complex queries exceeds that of state-of-the-art GraphRAG methods at comparable efficiency.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This suggests that global context during extraction is more important than local optimization for graph quality.
  • The multi-agent setup could be tested on domains with highly interconnected information, such as scientific literature.
  • Shared memory might allow fewer agents to achieve similar consistency if memory access is optimized.

Load-bearing premise

The shared-memory multi-agent society can reliably detect and resolve logical conflicts and maintain structural connectivity across an entire corpus during graph extraction.

What would settle it

A test on a large benchmark corpus where the graphs from MemGraphRAG still show unresolved logical conflicts or fragmentation, resulting in retrieval performance no better than baselines.

Figures

Figures reproduced from arXiv: 2606.00610 by Chuanjie Wu, Jinsong Su, Qinggang Zhang, Yunbo Tang, Zerui Chen, Zhishang Xiang.

Figure 1
Figure 1. Figure 1: Comparison between existing GraphRAG and Mem [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: (Left) Evaluation of representative RAG and [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Illustration of three conflict types in extracted [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Overview of the MemGraphRAG framework with two phases: (i) Memory-Based Indexing Graph Construction, where [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Ablation study of MemGraphRAG on three datasets. [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Multi-dimensional assessment of graph quality. [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: The prompt used for Conflict Detection Agent. [PITH_FULL_IMAGE:figures/full_fig_p018_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: The prompt used for Conflict Resolution Agent. [PITH_FULL_IMAGE:figures/full_fig_p019_8.png] view at source ↗
read the original abstract

Retrieval-Augmented Generation (RAG) has become an essential method for mitigating hallucinations in Large Language Models (LLMs) by leveraging external knowledge. Although effective for simple queries, traditional RAG struggles with large-scale, unstructured corpora where information is highly fragmented. Graph-based RAG (GraphRAG) incorporates knowledge graphs to capture structural relationships, enabling more comprehensive retrieval for complex reasoning. However, existing GraphRAG methods rely on isolated, fragment-level extraction for graph construction, lacking a global perspective on the whole corpus. As a result, these methods frequently lead to thematically inconsistent, logically conflicting, and structurally fragmented graphs that degrade retrieval performance. In this paper, we propose MemGraphRAG, a novel framework that introduces a memory-based multi-agent system to ensure high-quality graph construction. Specifically, MemGraphRAG employs a collaborative society of agents supported by shared memory, which provides a unified global context throughout the extraction process. This mechanism allows agents to dynamically resolve logical conflicts and maintain structural connectivity throughout the corpus. Furthermore, we propose a memory-aware hierarchical retrieval algorithm tailored for the constructed graph. Extensive experiments on multiple benchmarks demonstrate that MemGraphRAG outperforms the state-of-the-art baseline models with comparable efficiency. Our code is available at https://github.com/XMUDeepLIT/MemGraphRAG.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript proposes MemGraphRAG, a memory-based multi-agent framework for GraphRAG. It employs a collaborative society of agents with shared memory to supply unified global context during knowledge-graph extraction from large unstructured corpora, enabling dynamic resolution of logical conflicts and maintenance of structural connectivity. This is contrasted with prior fragment-level extraction methods that produce inconsistent and fragmented graphs. The work also introduces a memory-aware hierarchical retrieval algorithm. Experiments on multiple benchmarks are reported to show outperformance over state-of-the-art baselines at comparable efficiency; code is released.

Significance. If the shared-memory multi-agent mechanism can be shown to be the source of improved graph quality and retrieval performance, the approach would address a recognized limitation in existing GraphRAG pipelines for complex reasoning over fragmented corpora. The public release of code is a clear strength that supports reproducibility.

major comments (2)
  1. [Abstract and §3] Abstract and §3 (Method): The central claim that shared memory 'allows agents to dynamically resolve logical conflicts and maintain structural connectivity throughout the corpus' is load-bearing for attributing performance gains to the proposed mechanism rather than to hierarchical retrieval alone, yet no description of the conflict-detection algorithm, resolution protocol, or memory-update rules is supplied.
  2. [§5] §5 (Experiments): No metrics are reported that directly test the claimed mechanism, such as conflict counts before/after resolution, resolution success rate, inter-fragment consistency score, or a graph-fragmentation index comparing MemGraphRAG graphs to baselines; without these, it is impossible to confirm that the shared-memory component functions as asserted or drives the reported gains.
minor comments (2)
  1. Table captions and axis labels in the experimental figures should explicitly state the evaluation metrics and dataset names for immediate readability.
  2. The related-work section would benefit from a short paragraph contrasting MemGraphRAG specifically with other multi-agent or memory-augmented GraphRAG variants that have appeared since 2024.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. The comments highlight important areas for improving the description of our proposed mechanism and the evidence supporting its contribution. We address each major comment below and commit to revisions that will strengthen the paper without altering its core claims.

read point-by-point responses

  1. Referee: [Abstract and §3] Abstract and §3 (Method): The central claim that shared memory 'allows agents to dynamically resolve logical conflicts and maintain structural connectivity throughout the corpus' is load-bearing for attributing performance gains to the proposed mechanism rather than to hierarchical retrieval alone, yet no description of the conflict-detection algorithm, resolution protocol, or memory-update rules is supplied.

    Authors: We agree that the manuscript presents the shared-memory multi-agent system at a conceptual level in §3 without supplying the low-level algorithmic specifications. This limits the ability to fully attribute gains to the mechanism. In the revised manuscript we will add a new subsection to §3 that formally specifies the conflict-detection algorithm (semantic similarity plus LLM-based entailment verification), the resolution protocol (including agent querying of shared memory and arbitration rules), and the memory-update rules (with consistency checks and versioning). Pseudocode and a worked example from one of the corpora will be included. revision: yes

  2. Referee: [§5] §5 (Experiments): No metrics are reported that directly test the claimed mechanism, such as conflict counts before/after resolution, resolution success rate, inter-fragment consistency score, or a graph-fragmentation index comparing MemGraphRAG graphs to baselines; without these, it is impossible to confirm that the shared-memory component functions as asserted or drives the reported gains.

    Authors: We acknowledge that the current experimental section reports only end-to-end task performance and does not include direct diagnostics of the shared-memory mechanism. This is a fair observation. In the revision we will add a dedicated analysis subsection to §5 that reports conflict counts before and after resolution, resolution success rate, an inter-fragment consistency score, and a graph-fragmentation index, computed on the graphs produced by MemGraphRAG versus the baselines. These will be obtained via post-hoc analysis of the constructed knowledge graphs on the existing benchmark corpora. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical framework with experimental validation

full rationale

The paper proposes MemGraphRAG as a practical multi-agent system with shared memory for graph construction, claiming empirical outperformance on benchmarks. No derivation chain, equations, fitted parameters presented as predictions, or self-citation load-bearing steps exist in the provided text. The central mechanism is a design choice tested via experiments rather than reduced to its own inputs by construction. The result is self-contained as an engineering contribution.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no free parameters, axioms, or invented entities are described in sufficient detail to populate the ledger. The central claim rests on the unelaborated assumption that multi-agent memory sharing produces higher-quality graphs.

pith-pipeline@v0.9.1-grok · 5785 in / 1178 out tokens · 21184 ms · 2026-06-28T18:18:48.815295+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

95 extracted references · 43 canonical work pages · 17 internal anchors

  1. [1]

    Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Learning to retrieve, generate, and critique through self-reflection. In International Conference on Learning Representations (ICLR)

    2023

  2. [2]

    Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Ruther- ford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bog- dan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from trillions of tokens. InInternational Conference on Machine Learning (ICML)

    2022

  3. [3]

    ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

    Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, and Weipeng Chen. 2025. ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning. arXiv:2503.19470 [cs.AI] https://arxiv.org/ abs/2503.19470

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  4. [4]

    Shengyuan Chen, Zheng Yuan, Qinggang Zhang, Wen Hua, Jiannong Cao, and Xiao Huang. 2025. Neuro-Symbolic Entity Alignment via Variational Inference. The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)

    2025

  5. [5]

    Shengyuan Chen, Qinggang Zhang, Junnan Dong, Wen Hua, Qing Li, and Xiao Huang. 2024. Entity alignment with noisy annotations from large language models.The Thirty-Eighth Annual Conference on Neural Information Processing Systems(2024)

    2024

  6. [6]

    Shengyuan Chen, Chuang Zhou, Zheng Yuan, Qinggang Zhang, Zeyang Cui, Hao Chen, Yilin Xiao, Jiannong Cao, and Xiao Huang. 2025. You Don’t Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures.arXiv preprint arXiv:2508.06105(2025)

    work page arXiv 2025

  7. [7]

    CircleMind-AI. 2024. FastGraphRAG: High-speed graph-based retrieval- augmented generation.CircleMind-AI Blog(2024)

    2024

  8. [8]

    Jonathan Larson Darren Edge, Ha Trinh. 2024. LazyGraphRAG: Setting a new standard for quality and cost.Microsoft Blog(2024)

    2024

  9. [9]

    Junnan Dong, Siyu An, Yifei Yu, Qian-Wen Zhang, Linhao Luo, Xiao Huang, Yunsheng Wu, Di Yin, and Xing Sun. 2025. Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning. arXiv:2508.19855 https://arxiv.org/abs/2508.19855

    work page arXiv 2025

  10. [10]

    Su Dong, Qinggang Zhang, Yilin Xiao, Shengyuan Chen, Chuang Zhou, and Xiao Huang. 2026. Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs.arXiv preprint arXiv:2602.03578 (2026)

    work page arXiv 2026

  11. [11]

    Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models.arXiv e-prints(2024), arXiv–2407

    2024

  12. [12]

    Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization.arXiv preprint arXiv:2404.16130 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  13. [13]

    Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Shi Jie, Xiang Wang, Xiangnan He, and Tat-Seng Chua. 2024. Alphaedit: Null-space constrained knowledge editing for language models.arXiv preprint arXiv:2410.02355(2024)

    work page arXiv 2024

  14. [14]

    Junfeng Fang, Yukai Wang, Ruipeng Wang, Zijun Yao, Kun Wang, An Zhang, Xiang Wang, and Tat-Seng Chua. 2025. Safemlrm: Demystifying safety in multi- modal large reasoning models.arXiv preprint arXiv:2504.08813(2025)

    work page arXiv 2025

  15. [15]

    Linfeng Gao, Baolong Bi, Zheng Yuan, Le Wang, Zerui Chen, Zhimin Wei, Shenghua Liu, Qinggang Zhang, and Jinsong Su. 2025. Probing Latent Knowl- edge Conflict for Faithful Retrieval-Augmented Generation.arXiv preprint arXiv:2510.12460(2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  16. [16]

    Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey.arXiv preprint arXiv:2312.10997(2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  17. [17]

    Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, and Chao Huang. 2024. LightRAG: Simple and Fast Retrieval-Augmented Generation.arXiv preprint arXiv:2410.05779 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  18. [18]

    Anton Gusarov, Anastasia Volkova, Valentin Khrulkov, Andrey Kuznetsov, Ev- genii Maslov, and Ivan Oseledets. 2025. Multi-Agent GraphRAG: A Text-to- Cypher Framework for Labeled Property Graphs. arXiv:2511.08274 [cs.AI] https://arxiv.org/abs/2511.08274

    work page arXiv 2025

  19. [19]

    Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su

  20. [20]

    InAdvances in Neural Information Processing Systems (NeurIPS)

    HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Lan- guage Models. InAdvances in Neural Information Processing Systems (NeurIPS)

  21. [21]

    Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, and Yu Su. 2025. From rag to memory: Non-parametric continual learning for large language models.arXiv preprint arXiv:2502.14802(2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  22. [22]

    Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. REALM: Retrieval-Augmented Language Model Pre-Training. arXiv:2002.08909 [cs.CL] https://arxiv.org/abs/2002.08909

    work page internal anchor Pith review Pith/arXiv arXiv 2020

  23. [23]

    Haoyu Han, Harry Shomer, Yu Wang, Yongjia Lei, Kai Guo, Zhigang Hua, Bo Long, Hui Liu, and Jiliang Tang. 2025. Rag vs. graphrag: A systematic evaluation and key insights.arXiv preprint arXiv:2502.11371(2025)

    work page arXiv 2025

  24. [24]

    Haoyu Han, Yu Wang, Harry Shomer, Kai Guo, Jiayuan Ding, Yongjia Lei, Ma- hantesh Halappanavar, Ryan A Rossi, Subhabrata Mukherjee, Xianfeng Tang, et al

  25. [25]

    Retrieval-augmented generation with graphs (graphrag).arXiv preprint arXiv:2501.00309(2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  26. [26]

    Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. G-retriever: Retrieval-augmented KDD 2026, August 9–13, 2026, Jeju Island, Republic of Korea. Chuanjie Wu, Zhishang Xiang, Yunbo Tang, Zerui Chen, Qinggang Zhang, and Jinsong Su generation for textual graph understanding and question answe...

    work page arXiv 2024

  27. [27]

    Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps.arXiv preprint arXiv:2011.01060(2020)

    work page internal anchor Pith review Pith/arXiv arXiv 2020

  28. [28]

    Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, and Xiao Huang. 2024. Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL.arXiv preprint arXiv:2406.08426(2024)

    work page arXiv 2024

  29. [29]

    Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave

  30. [30]

    Atlas: Few-shot learning with retrieval augmented language models.The Journal of Machine Learning Research (JMLR)(2023)

    2023

  31. [31]

    Houcheng Jiang, Junfeng Fang, Ningyu Zhang, Guojun Ma, Mingyang Wan, Xiang Wang, Xiangnan He, and Tat-seng Chua. 2025. AnyEdit: Edit Any Knowledge Encoded in Language Models.ICML(2025)

    2025

  32. [32]

    Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Active retrieval augmented generation. InEmpirical Methods in Natural Language Processing (EMNLP)

    2023

  33. [33]

    Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning. arXiv:2503.09516 [cs.CL] https://arxiv.org/abs/2503.09516

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  34. [34]

    Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al

  35. [35]

    In Advances in Neural Information Processing Systems (NeurIPS)

    Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Processing Systems (NeurIPS)

  36. [36]

    Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025. Search-o1: Agentic Search-Enhanced Large Reasoning Models. arXiv:2501.05366 [cs.AI] https://arxiv.org/abs/2501.05366

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  37. [37]

    Lei Liang, Mengshu Sun, Zhengke Gui, Zhongshu Zhu, Zhouyu Jiang, Ling Zhong, Yuan Qu, Peilong Zhao, Zhongpu Bo, Jin Yang, et al. 2024. Kag: Boosting llms in professional domains via knowledge augmented generation.arXiv preprint arXiv:2409.13731(2024)

    work page arXiv 2024

  38. [38]

    Yujie Lin, Kunquan Li, YiXuan Liao, Xiaoxin Chen, and Jinsong Su. 2026. Bi- directional Bias Attribution: Debiasing Large Language Models without Modify- ing Prompts. InThe Fourteenth International Conference on Learning Representa- tions. https://openreview.net/forum?id=mUTN9VIaSy

    2026

  39. [39]

    Yujie Lin, Chengyi Yang, Zhishang Xiang, Yiping Song, and Jinsong Su. 2026. ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models. arXiv:2605.18879 [cs.LG] https://arxiv.org/abs/2605.18879

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  40. [40]

    LINHAO LUO, Yuan-Fang Li, Reza Haf, and Shirui Pan. 2024. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. InThe Twelfth International Conference on Learning Representations

    2024

  41. [41]

    Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Dinh Phung, Chen Gong, and Shirui Pan. 2025. GFM-RAG: graph foundation model for retrieval augmented generation.arXiv preprint arXiv:2502.01113(2025)

    work page arXiv 2025

  42. [42]

    Das, and Chengqi Zhang

    Renqiang Luo, Huafei Huang, Shuo Yu, Fengqi Yu, Feng Xia, Sajal K. Das, and Chengqi Zhang. 2026. Utility-Preserving Federated Graph Learning with Dual- Perspective Fairness.IEEE Transactions on Pattern Analysis and Machine Intelli- gence(2026)

    2026

  43. [43]

    Gabriel de Souza P Moreira, Radek Osmulski, Mengyao Xu, Ronay Ak, Benedikt Schifferer, and Even Oldridge. 2024. NV-Retriever: Improving text embedding models with effective hard-negative mining.arXiv preprint arXiv:2407.15831 (2024)

    work page arXiv 2024

  44. [44]

    OpenAI. 2023. GPT-4 Technical Report.OpenAI Blog(2023)

    2023

  45. [45]

    Tyler Thomas Procko and Omar Ochoa. 2024. Graph retrieval-augmented genera- tion for large language models: A survey. InConference on AI, Science, Engineering, and Technology (AIxSET)

    2024

  46. [46]

    Hongjin Qian, Zheng Liu, Peitian Zhang, Kelong Mao, Defu Lian, Zhicheng Dou, and Tiejun Huang. 2025. MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation. arXiv:2409.05591 [cs.CL] https://arxiv.org/abs/2409.05591

    work page arXiv 2025

  47. [47]

    Meng Qu and Jian Tang. 2019. Probabilistic Logic Neural Networks for Reason- ing. InAdvances in Neural Information Processing Systems (NeurIPS). Vancouver, Canada, 7710–7720

    2019

  48. [48]

    Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, and Christopher D. Manning. 2024. RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval. InInternational Conference on Learning Representations (ICLR)

    2024

  49. [49]

    Kartik Sharma, Peeyush Kumar, and Yunqing Li. 2024. OG-RAG: Ontology- Grounded Retrieval-Augmented Generation For Large Language Models.arXiv preprint arXiv:2412.15235(2024)

    work page arXiv 2024

  50. [50]

    Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In International Conference on Learning Representations (ICLR)

    2024

  51. [52]

    Transactions of the Association for Computational Linguistics10 (2022), 539–554

    MuSiQue: Multi-hop Questions via Single-hop Question Composition. Transactions of the Association for Computational Linguistics10 (2022), 539–554

    2022

  52. [53]

    Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal

  53. [54]

    InProceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers)

    Interleaving retrieval with chain-of-thought reasoning for knowledge- intensive multi-step questions. InProceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers). 10014–10037

  54. [55]

    Hong Ting Tsang, Jiaxin Bai, Haoyu Huang, Qiao Xiao, Tianshi Zheng, Baixuan Xu, Shujie Liu, and Yangqiu Song. 2025. AutoGraph-R1: End-to-End Reinforce- ment Learning for Knowledge Graph Construction. arXiv:2510.15339 [cs.CL] https://arxiv.org/abs/2510.15339

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  55. [56]

    Shu Wang, Yixiang Fang, Yingli Zhou, Xilin Liu, and Yuchi Ma. 2025. ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation. arXiv preprint arXiv:2502.09891(2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  56. [57]

    Yu Wang, Nedim Lipka, Ryan A Rossi, Alexa Siu, Ruiyi Zhang, and Tyler Derr

  57. [58]

    In Conference on Artificial Intelligence (AAAI)

    Knowledge graph prompting for multi-document question answering. In Conference on Artificial Intelligence (AAAI)

  58. [59]

    Zhishang Xiang, Chuanjie Wu, Qinggang Zhang, Shengyuan Chen, Zijin Hong, Xiao Huang, and Jinsong Su. 2025. When to use graphs in rag: A compre- hensive analysis for graph retrieval-augmented generation.arXiv preprint arXiv:2506.05690(2025)

    work page arXiv 2025

  59. [60]

    Zhishang Xiang, Chengyi Yang, Zerui Chen, Zhimin Wei, Yunbo Tang, Zongpei Teng, Zexi Peng, Zongxia Li, Chengsong Huang, Yicheng He, et al . 2026. A Systematic Survey of Self-Evolving Agents: From Model-Centric to Environment- Driven Co-Evolution. (2026)

    2026

  60. [61]

    Yilin Xiao, Chuang Zhou, Qinggang Zhang, Su Dong, Shengyuan Chen, and Xiao Huang. 2025. LAG: Logic-Augmented Generation from a Cartesian Perspective. arXiv preprint arXiv:2508.05509(2025)

    work page arXiv 2025

  61. [62]

    Yilin Xiao, Chuang Zhou, Qinggang Zhang, Bo Li, Qing Li, and Xiao Huang. 2025. Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs. arXiv:2506.10508 [cs.CL]

    work page arXiv 2025

  62. [63]

    Cehao Yang, Xiaojun Wu, Xueyuan Lin, Chengjin Xu, Xuhui Jiang, Yuanliang Sun, Jia Li, Hui Xiong, and Jian Guo. 2025. GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation. arXiv:2509.22009 [cs.CL] https://arxiv.org/abs/2509.22009

    work page arXiv 2025

  63. [64]

    Chang Yang, Chuang Zhou, Yilin Xiao, Su Dong, Luyao Zhuang, Yujing Zhang, Zhu Wang, Zijin Hong, Zheng Yuan, Zhishang Xiang, et al . 2026. Graph- based Agent Memory: Taxonomy, Techniques, and Applications.arXiv preprint arXiv:2602.05665(2026)

    work page arXiv 2026

  64. [65]

    Diji Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Jie Yang, and Yi Zhang. 2024. Im-rag: Multi-round retrieval-augmented generation through learning inner monologues. InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 730–740

    2024

  65. [66]

    Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. HotpotQA: A dataset for di- verse, explainable multi-hop question answering. InEmpirical Methods in Natural Language Processing (EMNLP)

    2018

  66. [67]

    Zheng Yuan, Hao Chen, Zijin Hong, Qinggang Zhang, Feiran Huang, Qing Li, and Xiao Huang. 2025. Knapsack optimization-based schema linking for llm-based Text-to-SQL generation.arXiv preprint arXiv:2502.12911(2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  67. [68]

    Fangyuan Zhang, Zhengjun Huang, Yingli Zhou, Qintian Guo, Zhixun Li, Wen- sheng Luo, Di Jiang, Yixiang Fang, and Xiaofang Zhou. 2025. EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora.arXiv preprint arXiv:2506.20963(2025)

    work page arXiv 2025

  68. [69]

    Qinggang Zhang, Shengyuan Chen, Yuanchen Bei, Zheng Yuan, Huachi Zhou, Zijin Hong, Junnan Dong, Hao Chen, Yi Chang, and Xiao Huang. 2025. A Sur- vey of Graph Retrieval-Augmented Generation for Customized Large Language Models.arXiv preprint arXiv:2501.13958(2025)

    work page arXiv 2025

  69. [70]

    Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, and Jinsong Su. 2025. FaithfulRAG: Fact-Level Conflict Modeling for Context- Faithful Retrieval-Augmented Generation.arXiv preprint arXiv:2506.08938(2025)

    work page arXiv 2025

  70. [71]

    Yibo Zhao, Jiapeng Zhu, Ye Guo, Kangkang He, and Xiang Li. 2025. Eˆ 2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness.arXiv preprint arXiv:2505.24226(2025)

    work page arXiv 2025

  71. [72]

    Baolin Zheng, Guanlin Chen, Hongqiong Zhong, Qingyang Teng, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, et al. 2025. USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models.arXiv preprint arXiv:2505.23793(2025)

    work page arXiv 2025

  72. [73]

    Qihuang Zhong, Haiyun Li, Luyao Zhuang, Juhua Liu, and Bo Du. 2024. Iterative data generation with large language models for aspect-based sentiment analysis. arXiv preprint arXiv:2407.00341(2024)

    work page arXiv 2024

  73. [74]

    Chulun Zhou, Qiujing Wang, Mo Yu, Xiaoqian Yue, Rui Lu, Jiangnan Li, Yifan Zhou, Shunchi Zhang, Jie Zhou, and Wai Lam. 2025. The essence of contex- tual understanding in theory of mind: A study on question answering with story characters. InProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 22612–22631

    2025

  74. [75]

    Chulun Zhou, Chunkang Zhang, Guoxin Yu, Fandong Meng, Jie Zhou, Wai Lam, and Mo Yu. 2025. Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling.arXiv preprint arXiv:2512.23959 (2025). MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation KDD 2026, August 9–13, 2026, Jeju Island, ...

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  75. [76]

    Yingli Zhou, Yaodong Su, Youran Sun, Shu Wang, Taotao Wang, Runyuan He, Yongwei Zhang, Sicong Liang, Xilin Liu, Yuchi Ma, et al. 2025. In-depth Analysis of Graph-based RAG in a Unified Framework.arXiv preprint arXiv:2503.04338 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  76. [77]

    exact phrase

    Luyao Zhuang, Shengyuan Chen, Yilin Xiao, Huachi Zhou, Yujing Zhang, Hao Chen, Qinggang Zhang, and Xiao Huang. 2025. LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora.arXiv preprint arXiv:2510.10114(2025). A Additional Experiments A.1 Ablation on Backbone LLMs To further evaluate the universality and robustness of MemGraphRAG, ...

    work page arXiv 2025

  77. [78]

    Newton was born in 1645

    Input Corpus Doc A:“Newton was born in 1645. ” Doc B:“Isaac Newton, born 1643... ” Same Corpus: Contains mutually exclusive facts due to source errors or extraction noise

  78. [79]

    Global Adjudication: 𝐴𝑑𝑒𝑡 detects Conflict:𝑇 1 ⊥𝑇 2 →𝐴 𝑟𝑒𝑠 checks Evidence (𝑀𝑝𝑎𝑠 ) →Update: Keep𝑇 2, Discard𝑇 1

    Graph Construction Isolated Extraction: 𝑇1 :(𝑁 𝑒𝑤𝑡𝑜𝑛, 𝑏𝑜𝑟𝑛_𝑖𝑛,1645) 𝑇2 :(𝑁 𝑒𝑤𝑡𝑜𝑛, 𝑏𝑜𝑟𝑛_𝑖𝑛,1643) →Both edges added to Graph𝐺. Global Adjudication: 𝐴𝑑𝑒𝑡 detects Conflict:𝑇 1 ⊥𝑇 2 →𝐴 𝑟𝑒𝑠 checks Evidence (𝑀𝑝𝑎𝑠 ) →Update: Keep𝑇 2, Discard𝑇 1

  79. [80]

    When was Isaac Newton born?

    Retrieval Query Q: “When was Isaac Newton born?”

  80. [81]

    Consistent Path: Query triggers verified node:{1643} →Trace back to𝑀 𝑝𝑎𝑠 evidence

    Retrieval Process Noisy Activation: Query triggers both nodes:{1645,1643} →Retriever fetches conflicting context. Consistent Path: Query triggers verified node:{1643} →Trace back to𝑀 𝑝𝑎𝑠 evidence

Showing first 80 references.