---
title: "You Don't Need Pre-built Graphs for RAG: Retrieval Augmented"
description: "The authors propose LogicRAG, which skips offline graph building and instead derives a structure for… 53 references, cited by 9 papers here."
authors: ["Shengyuan Chen", "Chuang Zhou", "Zheng Yuan", "Qinggang Zhang", "Zeyang Cui", "Hao Chen", "Yilin Xiao", "Jiannong Cao", "Xiao Huang"]
year: 2025
venue: "arXiv:2508.06105"
source: "https://arxiv.org/abs/2508.06105"
doi: "10.48550/arxiv.2508.06105"
arxiv: "2508.06105"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/chen-2025-don-t-need-pre-built/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chen-2025-don-t-need-pre-built/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/9/) / You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures

# You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures

**Authors:** [Shengyuan Chen](https://md.research.elamur.ai/free/en/authors/shengyuan-chen/), [Chuang Zhou](https://md.research.elamur.ai/free/en/authors/chuang-zhou/), [Zheng Yuan](https://md.research.elamur.ai/free/en/authors/zheng-yuan/), [Qinggang Zhang](https://md.research.elamur.ai/free/en/authors/qinggang-zhang/), Zeyang Cui, [Hao Chen](https://md.research.elamur.ai/free/en/authors/hao-chen/), [Yilin Xiao](https://md.research.elamur.ai/free/en/authors/yilin-xiao/), Jiannong Cao and [Xiao Huang](https://md.research.elamur.ai/free/en/authors/xiao-xia-huang/) · **Year:** 2025 · **Venue:** arXiv:2508.06105 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2508.06105) · [PDF](https://arxiv.org/pdf/2508.06105) · [DOI 10.48550/arxiv.2508.06105](https://doi.org/10.48550/arxiv.2508.06105) · [arXiv 2508.06105](https://arxiv.org/abs/2508.06105) · [OpenAlex](https://openalex.org/W4415192589)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [9](https://md.research.elamur.ai/free/en/papers/chen-2025-don-t-need-pre-built/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Graph-based RAG systems such as Microsoft GraphRAG, HippoRAG, RAPTOR, LightRAG and KGP first convert the entire corpus into a graph. This step consumes many LLM tokens and is slow to redo when documents change. The resulting graph may also not fit the reasoning pattern a given question needs. The authors propose LogicRAG, which skips offline graph building and instead derives a structure for each query at inference time.

An LLM uses few-shot prompting to split the question into subproblems and links them into a directed acyclic graph of dependencies. A topological sort then gives an order for answering the subproblems one at a time, with each retrieval conditioned on earlier answers. If the evidence for a node is insufficient, new subproblems are added on the fly. Two pruning mechanisms limit cost. Context pruning keeps a rolling LLM-written summary instead of accumulating raw passages, and graph pruning merges similar subproblems.

On multi-hop QA benchmarks (2WikiMQA, HotpotQA, MuSiQue), the authors report higher accuracy and better efficiency than strong baselines. This is useful wherever knowledge bases are large or change often.

## Key points
- On 2WikiMQA, query-time cost of LogicRAG is about 9.83 s and ~1,778 tokens per question. This compares with GraphRAG (13.05 s / ~4,700 tokens), LightRAG (35.14 s / ~5,731), KGP (70.72 s / ~11,098) and HippoRAG2 (5.89 s / ~2,809). These figures exclude the graph-construction cost that only the baselines incur.
- Accuracy on 2WikiMQA varies by question type:
  - comparison: 89%
  - bridge-comparison: 67%
  - compositional: 50% (this type makes up 44.4% of the questions)
  - inference: 39%
- On MuSiQue, accuracy drops steadily as the number of hops increases.
- Retrieval top-k shows diminishing returns: k = 3 or 5 gives the best balance of quality and cost. On MuSiQue, top-20 pushes the average cost above 6,000 tokens.
- Graph pruning reduces retrieval rounds across all question types, with the largest savings on compositional and multi-hop questions. 4-hop questions used fewer rounds than 3-hop ones, which the authors attribute to the LLM answering prematurely with partial evidence.
- Code is available at github.com/chensyCN/LogicRAG.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works

## Cite

Cite as: 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:2508.06105.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{chen2025you,
  title = {{You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures}},
  author = {Shengyuan Chen, Chuang Zhou, Zheng Yuan, Qinggang Zhang, Zeyang Cui, Hao Chen, Yilin Xiao, Jiannong Cao and Xiao Huang},
  year = {2025},
  doi = {10.48550/arxiv.2508.06105},
  eprint = {2508.06105},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2508.06105}
}
```

- [← previous VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models](https://md.research.elamur.ai/free/en/papers/cui-2025-voxeval-benchmarking-knowledge-understanding-capabilities/)
- [next → Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking](https://md.research.elamur.ai/free/en/papers/pisarevskaya-2025-zero-shot-few-shot-learning/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/9/)

## References

53 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Achiam, J.; Adler, S.; Agarwal, S.; Ahmad, L.; Akkaya, I.; Aleman, F. L.; Almeida, D.; Altenschmidt, J.; Altman, S.; Anadkat, S.; et al. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Anthropic. 2024. The Claude 3 Model Family: Opus, Sonnet, Haiku. Claude-3 Model Card. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024%2E+The+Claude+3+Model+Family%3A+Opus%2C+Sonnet%2C+Haiku%2E+Claude%2D3+Model+Card%2E)
3. Bei, Y.; Chen, H.; Chen, S.; Huang, X.; Zhou, S.; and Huang, F. 2023. Non-recursive cluster-scale graph interacted model for click-through rate prediction. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 3748–3752. [find](https://scholar.google.com/scholar?q=Bei%2C+Y%2E%3B+Chen%2C+H%2E%3B+Chen%2C+S%2E%3B+Huang%2C+X%2E%3B+Zhou%2C+S%2E%3B+and+Huang%2C+F%2E+2023%2E+Non%2Drecursive+cluster%2Dscale+graph+interacted+model+for+click%2Dthrough+rate+prediction%2E+In+Proceedings+of+the+32nd+ACM+International)
4. Borgeaud, S.; Mensch, A.; Hoffmann, J.; Cai, T.; Rutherford, E.; Millican, K.; Van Den Driessche, G. B.; Lespiau, J.-B.; Damoc, B.; Clark, A.; et al. 2022. Improving language models by retrieving from trillions of tokens. In International Conference on Machine Learning (ICML). [find](https://scholar.google.com/scholar?q=Borgeaud%2C+S%2E%3B+Mensch%2C+A%2E%3B+Hoffmann%2C+J%2E%3B+Cai%2C+T%2E%3B+Rutherford%2C+E%2E%3B+Millican%2C+K%2E%3B+Van+Den+Driessche%2C+G%2E+B%2E%3B+Lespiau%2C+J%2E%2DB%2E%3B+Damoc%2C+B%2E%3B+Clark%2C+A%2E%3B+et+al%2E+2022%2E+Improving+language+models+by+retrieving+from)
5. Chen, H.; Bei, Y.; Huang, W.; Chen, S.; Huang, F.; and Huang, X. 2024a. Graph cross-correlated network for recommendation. IEEE Transactions on Knowledge and Data Engineering. [find](https://scholar.google.com/scholar?q=Chen%2C+H%2E%3B+Bei%2C+Y%2E%3B+Huang%2C+W%2E%3B+Chen%2C+S%2E%3B+Huang%2C+F%2E%3B+and+Huang%2C+X%2E+2024a%2E+Graph+cross%2Dcorrelated+network+for+recommendation%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2E)
6. Chen, S.; Zhang, Q.; Dong, J.; Hua, W.; Cao, J.; and Huang, X. 2024b. Neuro-Symbolic Entity Alignment via Variational Inference. arXiv preprint arXiv:2410.04153. — [arXiv:2410.04153](https://arxiv.org/abs/2410.04153) [find](https://scholar.google.com/scholar?q=Chen%2C+S%2E%3B+Zhang%2C+Q%2E%3B+Dong%2C+J%2E%3B+Hua%2C+W%2E%3B+Cao%2C+J%2E%3B+and+Huang%2C+X%2E+2024b%2E+Neuro%2DSymbolic+Entity+Alignment+via+Variational+Inference%2E+arXiv+preprint+arXiv%3A2410%2E04153%2E+%E2%80%94+%5BarXiv%3A2410%2E04153%5D%28https%3A%2F%2Farxiv%2Eorg)
7. Chen, S.; Zhang, Q.; Dong, J.; Hua, W.; Li, Q.; and Huang, X. 2024c. Entity Alignment with Noisy Annotations from Large Language Models. arXiv preprint arXiv:2405.16806. — [arXiv:2405.16806](https://arxiv.org/abs/2405.16806) [find](https://scholar.google.com/scholar?q=Chen%2C+S%2E%3B+Zhang%2C+Q%2E%3B+Dong%2C+J%2E%3B+Hua%2C+W%2E%3B+Li%2C+Q%2E%3B+and+Huang%2C+X%2E+2024c%2E+Entity+Alignment+with+Noisy+Annotations+from+Large+Language+Models%2E+arXiv+preprint+arXiv%3A2405%2E16806%2E+%E2%80%94+%5BarXiv%3A2405%2E16806%5D%28https%3A%2F%2Fa)
8. Edge, D.; Trinh, H.; Cheng, N.; Bradley, J.; Chao, A.; Mody, A.; Truitt, S.; and Larson, J. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Edge%2C+D%2E%3B+Trinh%2C+H%2E%3B+Cheng%2C+N%2E%3B+Bradley%2C+J%2E%3B+Chao%2C+A%2E%3B+Mody%2C+A%2E%3B+Truitt%2C+S%2E%3B+and+Larson%2C+J%2E+2024%2E+From+local+to+global%3A+A+graph+rag+approach+to+query%2Dfocused+summarization%2E+arXiv+preprint+arXiv%3A2404%2E1)
9. Fang, J.; Jiang, H.; Wang, K.; Ma, Y.; Jie, S.; Wang, X.; He, X.; and Chua, T.-S. 2024. Alphaedit: Null-space constrained knowledge editing for language models. arXiv preprint arXiv:2410.02355. [find](https://scholar.google.com/scholar?q=Fang%2C+J%2E%3B+Jiang%2C+H%2E%3B+Wang%2C+K%2E%3B+Ma%2C+Y%2E%3B+Jie%2C+S%2E%3B+Wang%2C+X%2E%3B+He%2C+X%2E%3B+and+Chua%2C+T%2E%2DS%2E+2024%2E+Alphaedit%3A+Null%2Dspace+constrained+knowledge+editing+for+language+models%2E+arXiv+preprint+arXiv%3A2410%2E02355%2E)
10. Fang, J.; Wang, Y.; Wang, R.; Yao, Z.; Wang, K.; Zhang, A.; Wang, X.; and Chua, T.-S. 2025. Safemlrm: Demystifying safety in multi-modal large reasoning models. arXiv preprint arXiv:2504.08813. — [arXiv:2504.08813](https://arxiv.org/abs/2504.08813) [find](https://scholar.google.com/scholar?q=Fang%2C+J%2E%3B+Wang%2C+Y%2E%3B+Wang%2C+R%2E%3B+Yao%2C+Z%2E%3B+Wang%2C+K%2E%3B+Zhang%2C+A%2E%3B+Wang%2C+X%2E%3B+and+Chua%2C+T%2E%2DS%2E+2025%2E+Safemlrm%3A+Demystifying+safety+in+multi%2Dmodal+large+reasoning+models%2E+arXiv+preprint+arXiv%3A2504%2E08813%2E+%E2%80%94+%5BarX)
11. Fu, Y.; Peng, H.; Ou, L.; Sabharwal, A.; and Khot, T. 2023. [Specializing smaller language models towards multi-step reasoning](https://md.research.elamur.ai/free/en/papers/fu-2023-specializing-smaller-language-models-towards/). In International Conference on Machine Learning, 10421–10430.
12. PMLR. Gao, Y.; Xiong, Y.; Gao, X.; Jia, K.; Pan, J.; Bi, Y.; Dai, Y.; Sun, J.; and Wang, H. 2023. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). arXiv preprint arXiv:2312.10997.
13. Guo, K.; Shomer, H.; Zeng, S.; Han, H.; Wang, Y.; and Tang, J. 2025. [Empowering GraphRAG with Knowledge Filtering and Integration](https://md.research.elamur.ai/free/en/papers/guo-2025-empowering-graphrag-knowledge-filtering-integration/). arXiv preprint arXiv:2503.13804.
14. Guo, Z.; Xia, L.; Yu, Y.; Ao, T.; and Huang, C. 2024. [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://md.research.elamur.ai/free/en/papers/guo-2024-lightrag-simple-fast-retrieval-augmented/). arXiv preprint arXiv:2410.05779. Gutiérrez, B. J.; Shu, Y.; Gu, Y.; Yasunaga, M.; and Su, Y. 2024. HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models. In Adva…
15. He, X.; Tian, Y.; Sun, Y.; Chawla, N. V.; Laurent, T.; LeCun, Y.; Bresson, X.; and Hooi, B. 2024. [G-retriever: Retrieval-augmented generation for textual graph understanding and question answering](https://md.research.elamur.ai/free/en/papers/he-2024-g-retriever-retrieval-augmented-generation/). arXiv preprint arXiv:2402.07630.
16. Ho, X.; Nguyen, A.-K. D.; Sugawara, S.; and Aizawa, A. 2020. [Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps](https://md.research.elamur.ai/free/en/papers/ho-2020-constructing-multi-hop-qa-dataset/). arXiv preprint arXiv:2011.01060.
17. Hong, Z.; Yuan, Z.; Chen, H.; Zhang, Q.; Huang, F.; and Huang, X. 2024. Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM. In Findings of the Association for Computational Linguistics: ACL 2024. [find](https://scholar.google.com/scholar?q=Hong%2C+Z%2E%3B+Yuan%2C+Z%2E%3B+Chen%2C+H%2E%3B+Zhang%2C+Q%2E%3B+Huang%2C+F%2E%3B+and+Huang%2C+X%2E+2024%2E+Knowledge%2Dto%2DSQL%3A+Enhancing+SQL+Generation+with+Data+Expert+LLM%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+A)
18. Hong, Z.; Yuan, Z.; Zhang, Q.; Chen, H.; Dong, J.; Huang, F.; and Huang, X. 2025. Next-generation database interfaces: A survey of llm-based text-to-sql. IEEE Transactions on Knowledge and Data Engineering. [find](https://scholar.google.com/scholar?q=Hong%2C+Z%2E%3B+Yuan%2C+Z%2E%3B+Zhang%2C+Q%2E%3B+Chen%2C+H%2E%3B+Dong%2C+J%2E%3B+Huang%2C+F%2E%3B+and+Huang%2C+X%2E+2025%2E+Next%2Dgeneration+database+interfaces%3A+A+survey+of+llm%2Dbased+text%2Dto%2Dsql%2E+IEEE+Transactions+on+Knowledge+and+Data+Engine)
19. Huang, L.; Yu, W.; Ma, W.; Zhong, W.; Feng, Z.; Wang, H.; Chen, Q.; Peng, W.; Feng, X.; Qin, B.; et al. 2023. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems (TOIS).
20. Izacard, G.; Lewis, P.; Lomeli, M.; Hosseini, L.; Petroni, F.; Schick, T.; Dwivedi-Yu, J.; Joulin, A.; Riedel, S.; and Grave, E. 2023. [Atlas: Few-shot learning with retrieval augmented language models](https://md.research.elamur.ai/free/en/papers/izacard-2022-atlas-few-shot-learning-retrieval/). The Journal of Machine Learning Research (JMLR).
21. Jiang, Z.; Xu, F. F.; Gao, L.; Sun, Z.; Liu, Q.; Dwivedi-Yu, J.; Yang, Y.; Callan, J.; and Neubig, G. 2023. [Active retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/jiang-2023-active-retrieval-augmented-generation/). In Empirical Methods in Natural Language Processing (EMNLP).
22. Khashabi, D.; Min, S.; Khot, T.; Sabharwal, A.; Tafjord, O.; Clark, P.; and Hajishirzi, H. 2020. [Unifiedqa: Crossing format boundaries with a single qa system](https://md.research.elamur.ai/free/en/papers/khashabi-2020-unifiedqa-crossing-format-boundaries-single/). In Findings of Empirical Methods in Natural Language Processing (EMNLP). Lewis, P.; Perez, E.; Piktus, A.; Petroni, F.; Karpukhin, V.; Goyal…
23. Li, Y.; Li, W.; and Nie, L. 2021. A graph-guided multi-round retrieval method for conversational [open-domain question answering](https://md.research.elamur.ai/free/en/papers/chen-2020-open-domain-question-answering/). arXiv preprint arXiv:2104.08443. — [arXiv:2104.08443](https://arxiv.org/abs/2104.08443)
24. Li, Y.; Li, Z.; Wang, P.; Li, J.; Sun, X.; Cheng, H.; and Yu, J. X. 2023a. A survey of graph meets large language model: Progress and future directions. arXiv preprint arXiv:2311.12399. — [arXiv:2311.12399](https://arxiv.org/abs/2311.12399) [find](https://scholar.google.com/scholar?q=Li%2C+Y%2E%3B+Li%2C+Z%2E%3B+Wang%2C+P%2E%3B+Li%2C+J%2E%3B+Sun%2C+X%2E%3B+Cheng%2C+H%2E%3B+and+Yu%2C+J%2E+X%2E+2023a%2E+A+survey+of+graph+meets+large+language+model%3A+Progress+and+future+directions%2E+arXiv+preprint+arXiv%3A2311%2E12399%2E+%E2%80%94+%5BarXiv%3A2311%2E)
25. Li, Z.; Wang, L.; Sun, X.; Luo, Y.; Zhu, Y.; Chen, D.; Luo, Y.; Zhou, X.; Liu, Q.; Wu, S.; et al. 2023b. GSLB: the graph structure learning benchmark. Advances in Neural Information Processing Systems, 36: 30306–30318. [find](https://scholar.google.com/scholar?q=Li%2C+Z%2E%3B+Wang%2C+L%2E%3B+Sun%2C+X%2E%3B+Luo%2C+Y%2E%3B+Zhu%2C+Y%2E%3B+Chen%2C+D%2E%3B+Luo%2C+Y%2E%3B+Zhou%2C+X%2E%3B+Liu%2C+Q%2E%3B+Wu%2C+S%2E%3B+et+al%2E+2023b%2E+GSLB%3A+the+graph+structure+learning+benchmark%2E+Advances+in+Neural+Information+Processing+Systems)
26. Liu, Z.; Shengyuan, C.; Zhou, K.; Zha, D.; Huang, X.; and Hu, X. 2023. Rsc: accelerate graph neural networks training via randomized sparse computations. In International Conference on Machine Learning, 21951–21968. [find](https://scholar.google.com/scholar?q=Liu%2C+Z%2E%3B+Shengyuan%2C+C%2E%3B+Zhou%2C+K%2E%3B+Zha%2C+D%2E%3B+Huang%2C+X%2E%3B+and+Hu%2C+X%2E+2023%2E+Rsc%3A+accelerate+graph+neural+networks+training+via+randomized+sparse+computations%2E+In+International+Conference+on+Machine+Learnin)
27. PMLR. LlamaIndex. 2024. LlamaIndex - Build Knowledge Assistants over your Enterprise Data. [find](https://scholar.google.com/scholar?q=PMLR%2E+LlamaIndex%2E+2024%2E+LlamaIndex+%2D+Build+Knowledge+Assistants+over+your+Enterprise+Data%2E)
28. LlamaIndex Blog. Lu, Z.; Ding, K.; Zhang, Y.; Li, J.; Peng, B.; and Liu, L. 2021. Engage the public: Poll question generation for social media posts. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Lang… [find](https://scholar.google.com/scholar?q=LlamaIndex+Blog%2E+Lu%2C+Z%2E%3B+Ding%2C+K%2E%3B+Zhang%2C+Y%2E%3B+Li%2C+J%2E%3B+Peng%2C+B%2E%3B+and+Liu%2C+L%2E+2021%2E+Engage+the+public%3A+Poll+question+generation+for+social+media+posts%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+A)
29. Ma, S.; Xu, C.; Jiang, X.; Li, M.; Qu, H.; and Guo, J. 2024. Think-on-graph 2.0: Deep and interpretable large language model reasoning with knowledge graph-guided retrieval. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Ma%2C+S%2E%3B+Xu%2C+C%2E%3B+Jiang%2C+X%2E%3B+Li%2C+M%2E%3B+Qu%2C+H%2E%3B+and+Guo%2C+J%2E+2024%2E+Think%2Don%2Dgraph+2%2E0%3A+Deep+and+interpretable+large+language+model+reasoning+with+knowledge+graph%2Dguided+retrieval%2E+In+International+Conferenc)
30. OpenAI. 2023. [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/).
31. OpenAI Blog. Peng, B.; Zhu, Y.; Liu, Y.; Bo, X.; Shi, H.; Hong, C.; Zhang, Y.; and Tang, S. 2024. [Graph retrieval-augmented generation: A survey](https://md.research.elamur.ai/free/en/papers/peng-2024-graph-retrieval-augmented-generation-survey/). arXiv preprint arXiv:2408.08921.
32. Sarthi, P.; Abdullah, S.; Tuli, A.; Khanna, S.; Goldie, A.; and Manning, C. D. 2024. [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://md.research.elamur.ai/free/en/papers/sarthi-2024-raptor-recursive-abstractive-processing-tree/). In International Conference on Learning Representations (ICLR).
33. Shengyuan, C.; Cai, Y.; Fang, H.; Huang, X.; and Sun, M. 2024. Differentiable neuro-symbolic reasoning on large-scale knowledge graphs. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Shengyuan%2C+C%2E%3B+Cai%2C+Y%2E%3B+Fang%2C+H%2E%3B+Huang%2C+X%2E%3B+and+Sun%2C+M%2E+2024%2E+Differentiable+neuro%2Dsymbolic+reasoning+on+large%2Dscale+knowledge+graphs%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%2E)
34. Sun, J.; Xu, C.; Tang, L.; Wang, S.; Lin, C.; Gong, Y.; Ni, L.; Shum, H.-Y.; and Guo, J. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Sun%2C+J%2E%3B+Xu%2C+C%2E%3B+Tang%2C+L%2E%3B+Wang%2C+S%2E%3B+Lin%2C+C%2E%3B+Gong%2C+Y%2E%3B+Ni%2C+L%2E%3B+Shum%2C+H%2E%2DY%2E%3B+and+Guo%2C+J%2E+2024%2E+Think%2Don%2DGraph%3A+Deep+and+Responsible+Reasoning+of+Large+Language+Model+on+Knowledge+Graph%2E+In+Internation)
35. Trivedi, H.; Balasubramanian, N.; Khot, T.; and Sabharwal, A. 2022. [♪ MuSiQue: Multihop Questions via Single-hop Question Composition](https://md.research.elamur.ai/free/en/papers/trivedi-2022-musique-multihop-questions-single-hop/). Transactions of the Association for Computational Linguistics, 10: 539–554.
36. Trivedi, H.; Balasubramanian, N.; Khot, T.; and Sabharwal, A. 2023. [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/). In The 61st Annual Meeting Of The Association For Computational Linguistics.
37. Wang, Y.; Lipka, N.; Rossi, R. A.; Siu, A.; Zhang, R.; and Derr, T. 2024. Knowledge graph prompting for multi-document question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, 19206– 19214. [find](https://scholar.google.com/scholar?q=Wang%2C+Y%2E%3B+Lipka%2C+N%2E%3B+Rossi%2C+R%2E+A%2E%3B+Siu%2C+A%2E%3B+Zhang%2C+R%2E%3B+and+Derr%2C+T%2E+2024%2E+Knowledge+graph+prompting+for+multi%2Ddocument+question+answering%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intellige)
38. Wu, K.; Chen, H.; Wang, C.; Karray, F.; Li, Z.; Wang, Y.; and Zhong, F. 2025. Hierarchical Instruction-aware Embodied Visual Tracking. arXiv preprint arXiv:2505.20710. — [arXiv:2505.20710](https://arxiv.org/abs/2505.20710) [find](https://scholar.google.com/scholar?q=Wu%2C+K%2E%3B+Chen%2C+H%2E%3B+Wang%2C+C%2E%3B+Karray%2C+F%2E%3B+Li%2C+Z%2E%3B+Wang%2C+Y%2E%3B+and+Zhong%2C+F%2E+2025%2E+Hierarchical+Instruction%2Daware+Embodied+Visual+Tracking%2E+arXiv+preprint+arXiv%3A2505%2E20710%2E+%E2%80%94+%5BarXiv%3A2505%2E20710%5D%28https%3A%2F%2Farx)
39. Xiang, Z.; Wu, C.; Zhang, Q.; Chen, S.; Hong, Z.; Huang, X.; and Su, J. 2025. When to use graphs in rag: A comprehensive analysis for graph retrieval-augmented generation. arXiv preprint arXiv:2506.05690. — [arXiv:2506.05690](https://arxiv.org/abs/2506.05690) [find](https://scholar.google.com/scholar?q=Xiang%2C+Z%2E%3B+Wu%2C+C%2E%3B+Zhang%2C+Q%2E%3B+Chen%2C+S%2E%3B+Hong%2C+Z%2E%3B+Huang%2C+X%2E%3B+and+Su%2C+J%2E+2025%2E+When+to+use+graphs+in+rag%3A+A+comprehensive+analysis+for+graph+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2506%2E05)
40. Xiao, Y.; Zhou, C.; Zhang, Q.; Dong, S.; Chen, S.; and Huang, X. 2025a. LAG: Logic-Augmented Generation from a Cartesian Perspective. arXiv:2508.05509. — [arXiv:2508.05509](https://arxiv.org/abs/2508.05509) [find](https://scholar.google.com/scholar?q=Xiao%2C+Y%2E%3B+Zhou%2C+C%2E%3B+Zhang%2C+Q%2E%3B+Dong%2C+S%2E%3B+Chen%2C+S%2E%3B+and+Huang%2C+X%2E+2025a%2E+LAG%3A+Logic%2DAugmented+Generation+from+a+Cartesian+Perspective%2E+arXiv%3A2508%2E05509%2E+%E2%80%94+%5BarXiv%3A2508%2E05509%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2508%2E)
41. Xiao, Y.; Zhou, C.; Zhang, Q.; Li, B.; Li, Q.; and Huang, X. 2025b. Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs. arXiv:2506.10508. — [arXiv:2506.10508](https://arxiv.org/abs/2506.10508) [find](https://scholar.google.com/scholar?q=Xiao%2C+Y%2E%3B+Zhou%2C+C%2E%3B+Zhang%2C+Q%2E%3B+Li%2C+B%2E%3B+Li%2C+Q%2E%3B+and+Huang%2C+X%2E+2025b%2E+Reliable+Reasoning+Path%3A+Distilling+Effective+Guidance+for+LLM+Reasoning+with+Knowledge+Graphs%2E+arXiv%3A2506%2E10508%2E+%E2%80%94+%5BarXiv%3A2506%2E1050)
42. Yang, D.; Rao, J.; Chen, K.; Guo, X.; Zhang, Y.; Yang, J.; and Zhang, Y. 2024a. Im-rag: Multi-round retrieval-augmented generation through learning inner monologues. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 730–740. [find](https://scholar.google.com/scholar?q=Yang%2C+D%2E%3B+Rao%2C+J%2E%3B+Chen%2C+K%2E%3B+Guo%2C+X%2E%3B+Zhang%2C+Y%2E%3B+Yang%2C+J%2E%3B+and+Zhang%2C+Y%2E+2024a%2E+Im%2Drag%3A+Multi%2Dround+retrieval%2Daugmented+generation+through+learning+inner+monologues%2E+In+Proceedings+of+the+47th+Interna)
43. Yang, D.; Rao, J.; Chen, K.; Guo, X.; Zhang, Y.; Yang, J.; and Zhang, Y. 2024b. Im-rag: Multi-round retrieval-augmented generation through learning inner monologues. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 730–740. [find](https://scholar.google.com/scholar?q=Yang%2C+D%2E%3B+Rao%2C+J%2E%3B+Chen%2C+K%2E%3B+Guo%2C+X%2E%3B+Zhang%2C+Y%2E%3B+Yang%2C+J%2E%3B+and+Zhang%2C+Y%2E+2024b%2E+Im%2Drag%3A+Multi%2Dround+retrieval%2Daugmented+generation+through+learning+inner+monologues%2E+In+Proceedings+of+the+47th+Interna)
44. Yang, Z.; Qi, P.; Zhang, S.; Bengio, Y.; Cohen, W. W.; Salakhutdinov, R.; and Manning, C. D. 2018. [HotpotQA: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). In Empirical Methods in Natural Language Processing (EMNLP).
45. Zhang, F.; Huang, Z.; Zhou, Y.; Guo, Q.; Li, Z.; Luo, W.; Jiang, D.; Fang, Y.; and Zhou, X. 2025a. EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora. arXiv preprint arXiv:2506.20963. — [arXiv:2506.20963](https://arxiv.org/abs/2506.20963) [find](https://scholar.google.com/scholar?q=Zhang%2C+F%2E%3B+Huang%2C+Z%2E%3B+Zhou%2C+Y%2E%3B+Guo%2C+Q%2E%3B+Li%2C+Z%2E%3B+Luo%2C+W%2E%3B+Jiang%2C+D%2E%3B+Fang%2C+Y%2E%3B+and+Zhou%2C+X%2E+2025a%2E+EraRAG%3A+Efficient+and+Incremental+Retrieval+Augmented+Generation+for+Growing+Corpora%2E+arXiv+preprint+)
46. Zhang, Q.; Dong, J.; Chen, H.; Zha, D.; Yu, Z.; and Huang, X. 2024. Knowgpt: Knowledge graph based prompting for large language models. Advances in Neural Information Processing Systems, 37: 6052–6080. [find](https://scholar.google.com/scholar?q=Zhang%2C+Q%2E%3B+Dong%2C+J%2E%3B+Chen%2C+H%2E%3B+Zha%2C+D%2E%3B+Yu%2C+Z%2E%3B+and+Huang%2C+X%2E+2024%2E+Knowgpt%3A+Knowledge+graph+based+prompting+for+large+language+models%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A+6052%E2%80%936080)
47. Zhang, Q.; Xiang, Z.; Xiao, Y.; Wang, L.; Li, J.; Wang, X.; and Su, J. 2025b. [FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation](https://md.research.elamur.ai/free/en/papers/zhang-2025-faithfulrag-fact-level-conflict-modeling/). arXiv preprint arXiv:2506.08938.
48. Zhong, F.; Wu, K.; Wang, C.; Chen, H.; Ci, H.; Li, Z.; and Wang, Y. 2024. Unrealzoo: Enriching photo-realistic virtual worlds for embodied ai. arXiv preprint arXiv:2412.20977. — [arXiv:2412.20977](https://arxiv.org/abs/2412.20977) [find](https://scholar.google.com/scholar?q=Zhong%2C+F%2E%3B+Wu%2C+K%2E%3B+Wang%2C+C%2E%3B+Chen%2C+H%2E%3B+Ci%2C+H%2E%3B+Li%2C+Z%2E%3B+and+Wang%2C+Y%2E+2024%2E+Unrealzoo%3A+Enriching+photo%2Drealistic+virtual+worlds+for+embodied+ai%2E+arXiv+preprint+arXiv%3A2412%2E20977%2E+%E2%80%94+%5BarXiv%3A2412%2E20977%5D%28htt)
49. Zhou, C.; Wang, Z.; Chen, S.; Du, J.; Zheng, Q.; Xu, Z.; and Huang, X. 2025a. [Taming Language Models for Text-attributed Graph Learning with Decoupled Aggregation](https://md.research.elamur.ai/free/en/papers/zhou-2025-taming-language-models-text-attributed/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 3463–3474.
50. Zhou, H.; Du, J.; Zhou, C.; Yang, C.; Xiao, Y.; Xie, Y.; and Huang, X. 2025b. Each Graph is a New Language: Graph Learning with LLMs. arXiv preprint arXiv:2501.11478. [find](https://scholar.google.com/scholar?q=Zhou%2C+H%2E%3B+Du%2C+J%2E%3B+Zhou%2C+C%2E%3B+Yang%2C+C%2E%3B+Xiao%2C+Y%2E%3B+Xie%2C+Y%2E%3B+and+Huang%2C+X%2E+2025b%2E+Each+Graph+is+a+New+Language%3A+Graph+Learning+with+LLMs%2E+arXiv+preprint+arXiv%3A2501%2E11478%2E)
51. Zhou, H.; Yu, K.; Zhang, Q.; Chen, H.; Zha, D.; Pei, W.; Kong, A.; and Huang, X. 2025c. Self-Monitoring Large Language Models for Click-Through Rate Prediction. ACM Transactions on Information Systems, 44(1): 1–25. [find](https://scholar.google.com/scholar?q=Zhou%2C+H%2E%3B+Yu%2C+K%2E%3B+Zhang%2C+Q%2E%3B+Chen%2C+H%2E%3B+Zha%2C+D%2E%3B+Pei%2C+W%2E%3B+Kong%2C+A%2E%3B+and+Huang%2C+X%2E+2025c%2E+Self%2DMonitoring+Large+Language+Models+for+Click%2DThrough+Rate+Prediction%2E+ACM+Transactions+on+Information+Systems)
52. Zhou, Y.; Su, Y.; Sun, Y.; Wang, S.; Wang, T.; He, R.; Zhang, Y.; Liang, S.; Liu, X.; Ma, Y.; et al. 2025d. In-depth Analysis of Graph-based RAG in a Unified Framework. arXiv preprint arXiv:2503.04338. — [arXiv:2503.04338](https://arxiv.org/abs/2503.04338) [find](https://scholar.google.com/scholar?q=Zhou%2C+Y%2E%3B+Su%2C+Y%2E%3B+Sun%2C+Y%2E%3B+Wang%2C+S%2E%3B+Wang%2C+T%2E%3B+He%2C+R%2E%3B+Zhang%2C+Y%2E%3B+Liang%2C+S%2E%3B+Liu%2C+X%2E%3B+Ma%2C+Y%2E%3B+et+al%2E+2025d%2E+In%2Ddepth+Analysis+of+Graph%2Dbased+RAG+in+a+Unified+Framework%2E+arXiv+preprint+arXiv%3A2503%2E04338)
53. Zhuang, L.; Chen, S.; Xiao, Y.; Zhou, H.; Zhang, Y.; Chen, H.; Zhang, Q.; and Huang, X. 2025. LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora. arXiv preprint arXiv:2510.10114. — [arXiv:2510.10114](https://arxiv.org/abs/2510.10114) [find](https://scholar.google.com/scholar?q=Zhuang%2C+L%2E%3B+Chen%2C+S%2E%3B+Xiao%2C+Y%2E%3B+Zhou%2C+H%2E%3B+Zhang%2C+Y%2E%3B+Chen%2C+H%2E%3B+Zhang%2C+Q%2E%3B+and+Huang%2C+X%2E+2025%2E+LinearRAG%3A+Linear+Graph+Retrieval+Augmented+Generation+on+Large%2Dscale+Corpora%2E+arXiv+preprint+arXiv%3A2510%2E1)

*Updated 1 November 2026*