---
title: "ViDoRAG — paper by Wang et al. (2025) — summary and ideas"
description: "To fill this gap, the authors build ViDoSeek, a benchmark in which every query has a single answer… 35 references, cited by 25 papers here."
authors: ["Qiuchen Wang", "Ruixue Ding", "Zehui Chen", "Weiqi Wu", "Shihang Wang", "Pengjun Xie", "Feng Zhao"]
year: 2025
venue: "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/2025.emnlp-main.464/"
doi: "10.18653/v1/2025.emnlp-main.464"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2025-vidorag-visual-document-retrieval-augmented/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2025-vidorag-visual-document-retrieval-augmented/)

[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/2/) / ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

# ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

**Authors:** [Qiuchen Wang](https://md.research.elamur.ai/free/en/authors/qiuchen-wang/), [Ruixue Ding](https://md.research.elamur.ai/free/en/authors/ruixue-ding/), [Zehui Chen](https://md.research.elamur.ai/free/en/authors/zehui-chen/), Weiqi Wu, [Shihang Wang](https://md.research.elamur.ai/free/en/authors/shihang-wang/), [Pengjun Xie](https://md.research.elamur.ai/free/en/authors/pengjun-xie/) and [Feng Zhao](https://md.research.elamur.ai/free/en/authors/feng-zhao/) · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.emnlp-main.464/) · [PDF](https://aclanthology.org/2025.emnlp-main.464.pdf) · [DOI 10.18653/v1/2025.emnlp-main.464](https://doi.org/10.18653/v1/2025.emnlp-main.464) · [OpenAlex](https://openalex.org/W4416036851)

**Citations:** 14 citations (OpenAlex, 2026-10-14) · [25](https://md.research.elamur.ai/free/en/papers/wang-2025-vidorag-visual-document-retrieval-augmented/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses retrieval-augmented generation (RAG) over large collections of visually rich documents such as slides with charts, tables and diagrams. Existing VQA benchmarks usually pair each question with one image or one document, so answers may not be unique across a whole corpus. Such benchmarks therefore cannot properly test retrieval. To fill this gap, the authors build ViDoSeek, a benchmark in which every query has a single answer and specific reference pages within a pool of roughly 6k page images.

They also propose ViDoRAG, which has two parts:
- **Retrieval:** a hybrid step that merges visual and textual results and uses a Gaussian Mixture Model to decide how many pages to keep for each query.
- **Generation:** a coarse-to-fine, actor-critic loop with three agents. The seeker picks candidate pages, the inspector checks them and gives feedback, and the answer agent produces a consistent final response.

ViDoRAG beats strong baselines on ViDoSeek by more than 10%. The work matters because it offers a realistic testbed for document RAG and a practical way to scale reasoning at test time.

## Key points
- ViDoSeek combines newly annotated queries over 300 English slide decks (25–50 pages each, 12 domains, e.g. economics and geography) with refined queries from SlideVQA.
- The dataset was built in four stages: document collection, expert query writing, automatic quality review with GPT-4, and multimodal refinement with GPT-4o.
- GMM-based dynamic retrieval raised accuracy from 72.1 to 72.8 while cutting the average number of retrieved pages from 10 to 6.76.
- Vision-based pipelines beat text-based ones on every query type, including text-centric questions. Stronger models (GPT-4o, Qwen2.5-VL-72B) needed fewer seeker–inspector rounds than weaker ones (Qwen2.5-VL-7B, Llama3.2-Vision-11B).
- The authors acknowledge three limitations: added latency from the iterative agents, possible bias from expert-written queries, and remaining hallucinations. Code is available at github.com/Alibaba-NLP/ViDoRAG.

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

## Institutions

- [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 149 works · 16,161 citations
- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 108 works · 112,698 citations

📚 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: Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie and Feng Zhao. 2025. ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{wang2025vidorag,
  title = {{ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents}},
  author = {Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie and Feng Zhao},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.464},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.464}
}
```

- [← previous NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model](https://md.research.elamur.ai/free/en/papers/basant-2025-nvidia-nemotron-nano-2-accurate/)
- [next → CulturalBench: A Robust, Diverse and Challenging Benchmark for Measuring LMs' Cultural Knowledge Through Human-AI Red-Teaming](https://md.research.elamur.ai/free/en/papers/chiu-2025-culturalbench-robust-diverse-challenging-benchmark/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/)

## References

35 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rishabh Agarwal, Avi Singh, Lei Zhang, Bernd Bohnet, Luis Rosias, Stephanie Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, et al. 2025. [Many-shot in-context learning](https://md.research.elamur.ai/free/en/papers/agarwal-2024-many-shot-context-learning/). In Advances in Neural Information Processing Systems, 37:76930– 76966.
2. Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh. 2015. Vqa: Visual question answering. In Proceedings of the IEEE International Conference on Computer Vision, pages 2425–2433. [find](https://scholar.google.com/scholar?q=Stanislaw+Antol%2C+Aishwarya+Agrawal%2C+Jiasen+Lu%2C+Margaret+Mitchell%2C+Dhruv+Batra%2C+C+Lawrence+Zitnick%2C+and+Devi+Parikh%2E+2015%2E+Vqa%3A+Visual+question+answering%2E+In+Proceedings+of+the+IEEE+International+Confe)
3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). In Advances in Neural Information Processing Systems, 33:1877–1901.
4. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024a. [Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/). arXiv preprint arXiv:2402.03216.
5. Zehui Chen, Kuikun Liu, Qiuchen Wang, Jiangning Liu, Wenwei Zhang, Kai Chen, and Feng Zhao. 2024b. [Mindsearch: Mimicking human minds elicits deep ai searcher](https://md.research.elamur.ai/free/en/papers/chen-2024-mindsearch-mimicking-human-minds-elicits/). arXiv preprint arXiv:2407.20183.
6. Yixiong Fang, Tianran Sun, Yuling Shi, and Xiaodong Gu. 2025a. Attentionrag: Attention-guided context pruning in retrieval-augmented generation. arXiv preprint arXiv:2503.10720. \#\# Ethical Considerations Yixiong Fang, Tianran Sun, Yuling Shi, Min Wang, and Xiaodong Gu. 2025b. Lastingbench: Defend be… [find](https://scholar.google.com/scholar?q=Yixiong+Fang%2C+Tianran+Sun%2C+Yuling+Shi%2C+and+Xiaodong+Gu%2E+2025a%2E+Attentionrag%3A+Attention%2Dguided+context+pruning+in+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2503%2E10720%2E+%5C%23%5C%23+Ethical+Considera)
7. Our data does not contain any private or sensitive information, and all content is derived from publicly Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Céline Hudelot, and Pierre Colombo. 2024. Colpali: Efficient document retrieval with vision language models. arXiv preprint ar… [find](https://scholar.google.com/scholar?q=Our+data+does+not+contain+any+private+or+sensitive+information%2C+and+all+content+is+derived+from+publicly+Manuel+Faysse%2C+Hugues+Sibille%2C+Tony+Wu%2C+Bilel+Omrani%2C+Gautier+Viaud%2C+C%C3%A9line+Hudelot%2C+and+Pierre)
8. Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2021. Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943. [find](https://scholar.google.com/scholar?q=Sewon+Min%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Hannaneh+Hajishirzi%2E+2021%2E+Metaicl%3A+Learning+to+learn+in+context%2E+arXiv+preprint+arXiv%3A2110%2E15943%2E)
9. Ziyan Jiang, Xueguang Ma, and Wenhu Chen. 2024. Longrag: Enhancing retrieval-augmented generation with long-context llms. arXiv preprint arXiv:2406.15319. — [arXiv:2406.15319](https://arxiv.org/abs/2406.15319) [find](https://scholar.google.com/scholar?q=Ziyan+Jiang%2C+Xueguang+Ma%2C+and+Wenhu+Chen%2E+2024%2E+Longrag%3A+Enhancing+retrieval%2Daugmented+generation+with+long%2Dcontext+llms%2E+arXiv+preprint+arXiv%3A2406%2E15319%2E+%E2%80%94+%5BarXiv%3A2406%2E15319%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F24)
10. Stephen Robertson, Hugo Zaragoza, et al. 2009. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends® in Information Retrieval, 3(4):333–389. [find](https://scholar.google.com/scholar?q=Stephen+Robertson%2C+Hugo+Zaragoza%2C+et+al%2E+2009%2E+The+probabilistic+relevance+framework%3A+Bm25+and+beyond%2E+Foundations+and+Trends%C2%AE+in+Information+Retrieval%2C+3%284%29%3A333%E2%80%93389%2E)
11. Chankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2024. [Nv-embed: Improved techniques for training llms as generalist embedding models](https://md.research.elamur.ai/free/en/papers/lee-2024-nv-embed-improved-techniques-training/). arXiv preprint arXiv:2405.17428.
12. Rulin Shao, Jacqueline He, Akari Asai, Weijia Shi, Tim Dettmers, Sewon Min, Luke Zettlemoyer, and Pang Wei W Koh. 2025. Scaling retrieval-based language models with a trillion-token datastore. In Advances in Neural Information Processing Systems, 37:91260– 91299. [find](https://scholar.google.com/scholar?q=Rulin+Shao%2C+Jacqueline+He%2C+Akari+Asai%2C+Weijia+Shi%2C+Tim+Dettmers%2C+Sewon+Min%2C+Luke+Zettlemoyer%2C+and+Pang+Wei+W+Koh%2E+2025%2E+Scaling+retrieval%2Dbased+language+models+with+a+trillion%2Dtoken+datastore%2E+In+Adva)
13. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Processing Systems, 33:9459– 947…
14. Ryota Tanaka, Kyosuke Nishida, Kosuke Nishida, Taku Hasegawa, Itsumi Saito, and Kuniko Saito. 2023. Slidevqa: A dataset for document visual question answering on multiple images. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 13636–13645. [find](https://scholar.google.com/scholar?q=Ryota+Tanaka%2C+Kyosuke+Nishida%2C+Kosuke+Nishida%2C+Taku+Hasegawa%2C+Itsumi+Saito%2C+and+Kuniko+Saito%2E+2023%2E+Slidevqa%3A+A+dataset+for+document+visual+question+answering+on+multiple+images%2E+In+Proceedings+of+the)
15. Lei Li, Yuqi Wang, Runxin Xu, Peiyi Wang, Xiachong Feng, Lingpeng Kong, and Qi Liu. 2024. [Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models](https://md.research.elamur.ai/free/en/papers/li-2024-multimodal-arxiv-dataset-improving-scientific/). arXiv preprint arXiv:2403.00231.
16. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024. [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-team-2024-gemini-1-5-unlocking-multimodal/). arXiv preprint arXiv:2403.05530.
17. Yanjun Ma, Dianhai Yu, Tian Wu, and Haifeng Wang. 2019. Paddlepaddle: An open-source deep learning platform from industrial practice. Frontiers of Data and Domputing, 1(1):105–115. [find](https://scholar.google.com/scholar?q=Yanjun+Ma%2C+Dianhai+Yu%2C+Tian+Wu%2C+and+Haifeng+Wang%2E+2019%2E+Paddlepaddle%3A+An+open%2Dsource+deep+learning+platform+from+industrial+practice%2E+Frontiers+of+Data+and+Domputing%2C+1%281%29%3A105%E2%80%93115%2E)
18. Yubo Ma, Yuhang Zang, Liangyu Chen, Meiqi Chen, Yizhu Jiao, Xinze Li, Xinyuan Lu, Ziyu Liu, Yan Ma, Xiaoyi Dong, Pan Zhang, Liangming Pan, Yu-Gang Jiang, Jiaqi Wang, Yixin Cao, and Aixin Sun. 2024. Mmlongbench-doc: Benchmarking long-context document understanding with visualizations. Preprint, arXiv… [find](https://scholar.google.com/scholar?q=Yubo+Ma%2C+Yuhang+Zang%2C+Liangyu+Chen%2C+Meiqi+Chen%2C+Yizhu+Jiao%2C+Xinze+Li%2C+Xinyuan+Lu%2C+Ziyu+Liu%2C+Yan+Ma%2C+Xiaoyi+Dong%2C+Pan+Zhang%2C+Liangming+Pan%2C+Yu%2DGang+Jiang%2C+Jiaqi+Wang%2C+Yixin+Cao%2C+and+Aixin+Sun%2E+2024%2E+Mm)
19. Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. [Chartqa: A benchmark for question answering about charts with visual and logical reasoning](https://md.research.elamur.ai/free/en/papers/masry-2022-chartqa-benchmark-question-answering-about/). arXiv preprint arXiv:2203.10244.
20. Minesh Mathew, Viraj Bagal, Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny, and CV Jawahar. 2022. Infographicvqa. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1697–1706. [find](https://scholar.google.com/scholar?q=Minesh+Mathew%2C+Viraj+Bagal%2C+Rub%C3%A8n+Tito%2C+Dimosthenis+Karatzas%2C+Ernest+Valveny%2C+and+CV+Jawahar%2E+2022%2E+Infographicvqa%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on+Applications+of+Computer+Vision%2C)
21. Minesh Mathew, Dimosthenis Karatzas, and CV Jawahar. 2021. [Docvqa: A dataset for vqa on document images](https://md.research.elamur.ai/free/en/papers/mathew-2020-docvqa-dataset-vqa-document-images/). In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2200–2209.
22. Nitesh Methani, Pritha Ganguly, Mitesh M Khapra, and Pratyush Kumar. 2020. Plotqa: Reasoning over scientific plots. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1527–1536. [find](https://scholar.google.com/scholar?q=Nitesh+Methani%2C+Pritha+Ganguly%2C+Mitesh+M+Khapra%2C+and+Pratyush+Kumar%2E+2020%2E+Plotqa%3A+Reasoning+over+scientific+plots%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on+Applications+of+Computer+Vision%2C)
23. Minzheng Wang, Longze Chen, Fu Cheng, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, et al. 2024. [Leave no document behind: Benchmarking long-context llms with extended multi-doc qa](https://md.research.elamur.ai/free/en/papers/wang-2024-leave-no-document-behind-benchmarking/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Proce…
24. Qiuchen Wang, Ruixue Ding, Yu Zeng, Zehui Chen, Lin Chen, Shihang Wang, Pengjun Xie, Fei Huang, and Feng Zhao. 2025. [Vrag-rl: Empower vision-perception-based rag for visually rich information understanding via iterative reasoning with reinforcement learning](https://md.research.elamur.ai/free/en/papers/wang-2025-vrag-rl-empower-vision-perception/). arXiv preprint arXiv:2505.22019.
25. Shi Weijia, Min Sewon, Yasunaga Michihiro, Seo Minjoon, James Rich, Lewis Mike, and Yih Wen-tau. 2023. [Replug: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). ArXiv: 2301.12652.
26. Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Deyu Zhou, Pengjun Xie, and Fei Huang. 2025. [Webwalker: Benchmarking llms in web traversal](https://md.research.elamur.ai/free/en/papers/wu-2025-webwalker-benchmarking-llms-web-traversal/). arXiv preprint arXiv:2501.07572.
27. Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan Liu, Sandeep Subramanian, Evelina Bakhturina, Mohammad Shoeybi, and Bryan Catanzaro. 2023. [Retrieval meets long context large language models](https://md.research.elamur.ai/free/en/papers/xu-2023-retrieval-meets-long-context-large/). arXiv preprint arXiv:2310.03025.
28. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+et+al%2E+2024%2E+Qwen2%2E+5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115%2E)
29. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). arXiv preprint arXiv:2210.03629.
30. Jiabo Ye, Haiyang Xu, Haowei Liu, Anwen Hu, Ming Yan, Qi Qian, Ji Zhang, Fei Huang, and Jingren Zhou. 2024. mplug-owl3: Towards long image-sequence understanding in multi-modal large language models. arXiv preprint arXiv:2408.04840. [find](https://scholar.google.com/scholar?q=Jiabo+Ye%2C+Haiyang+Xu%2C+Haowei+Liu%2C+Anwen+Hu%2C+Ming+Yan%2C+Qi+Qian%2C+Ji+Zhang%2C+Fei+Huang%2C+and+Jingren+Zhou%2E+2024%2E+mplug%2Dowl3%3A+Towards+long+image%2Dsequence+understanding+in+multi%2Dmodal+large+language+models%2E+)
31. Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, et al. 2024a. Visrag: Vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594. — [arXiv:2410.10594](https://arxiv.org/abs/2410.10594) [find](https://scholar.google.com/scholar?q=Shi+Yu%2C+Chaoyue+Tang%2C+Bokai+Xu%2C+Junbo+Cui%2C+Junhao+Ran%2C+Yukun+Yan%2C+Zhenghao+Liu%2C+Shuo+Wang%2C+Xu+Han%2C+Zhiyuan+Liu%2C+et+al%2E+2024a%2E+Visrag%3A+Vision%2Dbased+retrieval%2Daugmented+generation+on+multi%2Dmodality+docu)
32. Tan Yu, Anbang Xu, and Rama Akkiraju. 2024b. In defense of rag in the era of long-context language models. arXiv preprint arXiv:2409.01666. — [arXiv:2409.01666](https://arxiv.org/abs/2409.01666) [find](https://scholar.google.com/scholar?q=Tan+Yu%2C+Anbang+Xu%2C+and+Rama+Akkiraju%2E+2024b%2E+In+defense+of+rag+in+the+era+of+long%2Dcontext+language+models%2E+arXiv+preprint+arXiv%3A2409%2E01666%2E+%E2%80%94+%5BarXiv%3A2409%2E01666%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2409%2E01666%29)
33. Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, and Michael Bendersky. 2024. Inference scaling for long-context retrieval augmented generation. arXiv preprint arXiv:2410.04343. — [arXiv:2410.04343](https://arxiv.org/abs/2410.04343) [find](https://scholar.google.com/scholar?q=Zhenrui+Yue%2C+Honglei+Zhuang%2C+Aijun+Bai%2C+Kai+Hui%2C+Rolf+Jagerman%2C+Hansi+Zeng%2C+Zhen+Qin%2C+Dong+Wang%2C+Xuanhui+Wang%2C+and+Michael+Bendersky%2E+2024%2E+Inference+scaling+for+long%2Dcontext+retrieval+augmented+gener)
34. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. 2023. [Sigmoid loss for language image pre-training](https://md.research.elamur.ai/free/en/papers/zhai-2023-sigmoid-loss-language-image-pre/). In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 11975–11986.
35. Huan Zhang, Yu Song, Ziyu Hou, Santiago Miret, and Bang Liu. 2024. Honeycomb: A flexible llm-based agent system for materials science. arXiv preprint arXiv:2409.00135. [find](https://scholar.google.com/scholar?q=Huan+Zhang%2C+Yu+Song%2C+Ziyu+Hou%2C+Santiago+Miret%2C+and+Bang+Liu%2E+2024%2E+Honeycomb%3A+A+flexible+llm%2Dbased+agent+system+for+materials+science%2E+arXiv+preprint+arXiv%3A2409%2E00135%2E)

*Updated 31 October 2026*