---
title: "SURVEYFORGE — paper by Yan et al. (2025)"
description: "The authors also build SurveyBench, a benchmark of 100 human-written surveys that scores… 36 references, cited by 12 papers here."
authors: ["Xiangchao Yan", "Shiyang Feng", "Jiakang Yuan", "Renqiu Xia", "Bin Wang", "Lei Bai", "Bo Zhang"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.609/"
doi: "10.18653/v1/2025.acl-long.609"
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/yan-2025-surveyforge-outline-heuristics-memory-driven/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yan-2025-surveyforge-outline-heuristics-memory-driven/)

[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/5/) / SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

# SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

**Authors:** Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, [Bin Wang](https://md.research.elamur.ai/free/en/authors/bin-wang/), [Lei Bai](https://md.research.elamur.ai/free/en/authors/lei-bai/) and [Bo Zhang](https://md.research.elamur.ai/free/en/authors/bo-zhang/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.609/) · [PDF](https://aclanthology.org/2025.acl-long.609.pdf) · [DOI 10.18653/v1/2025.acl-long.609](https://doi.org/10.18653/v1/2025.acl-long.609) · [OpenAlex](https://openalex.org/W4412945309)

**Citations:** 8 citations (OpenAlex, 2026-10-14) · [12](https://md.research.elamur.ai/free/en/papers/yan-2025-surveyforge-outline-heuristics-memory-driven/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLM-written literature surveys still lag well behind human ones. Their outlines are often badly organized, with sections too broad, too narrow, too deep or too shallow. Their reference lists tend to include marginal works and miss the field's most influential papers. Evaluation of such systems has also mostly relied on coarse, holistic LLM judgments. SURVEYFORGE addresses these problems with a two-stage pipeline. In the outline stage, it retrieves topic-relevant papers together with outlines of existing human-authored surveys and borrows their structural patterns. In the content stage, a memory-driven Scholar Navigation Agent (SANA) splits each subsection into sub-queries, retrieves candidate literature and reranks it with a time-aware engine. The resulting subsection texts are then merged and polished into one survey. The authors also build SurveyBench, a benchmark of 100 human-written surveys that scores reference, outline and content quality and supports win-rate comparisons. SURVEYFORGE outperforms AutoSurvey, and the automatic scores closely track expert opinion. This makes the system a practical aid for researchers entering unfamiliar fields.

## Key points
- **Resources:** code is on GitHub (Alpha-Innovator/SurveyForge) and the benchmark is on Hugging Face (U4R/SurveyBench). SurveyBench evaluates three dimensions: reference, outline and content quality.
- **Human validation:** 20 computer-science PhD experts compared SURVEYFORGE with AutoSurvey.
  - Outline quality: automatic Score/Comparative Win Rates of 73%/75%, versus 74% from the experts.
  - Content quality: automatic 69%, versus 70% from the experts.
  - A Cohen's kappa analysis also showed strong agreement.
- **Outline ablation (Claude-3-haiku-20240307, 10 topics × 3 runs):** the outline score rises step by step.
  - 81.78 with retrieved papers only.
  - 84.58 when random survey outlines are added as guidance.
  - 86.67 with domain-specific survey outlines.
- **SANA components:** memory for retrieval (MR), memory for sub-queries (MS) and the Temporal-aware Reranking Engine (TRE). Each improves the quality of retrieved literature and, in turn, of the cited references.
- **Limitations:** the system shows weak cross-source synthesis and little critical or forward-looking analysis. Hallucinations can still affect both the content and the citations.

*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 (7): [🖥️ 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 577 works

## Cite

Cite as: Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, Bin Wang, Lei Bai and Bo Zhang. 2025. SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{yan2025surveyforge,
  title = {{SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing}},
  author = {Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, Bin Wang, Lei Bai and Bo Zhang},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.609},
  url = {https://doi.org/10.18653/v1/2025.acl-long.609}
}
```

- [← previous SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment](https://md.research.elamur.ai/free/en/papers/fan-2025-slam-efficient-multilingual-reasoning-selective/)
- [next → The AI Gap: How Socioeconomic Status Affects Language Technology Interactions](https://md.research.elamur.ai/free/en/papers/bassignana-2025-ai-gap-how-socioeconomic-status/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/5/)

## References

36 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, 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. URL: [https://www-cdn.anthropic.com/](https://www-cdn.anthropic.com/) de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/ Model_Card_Claude_3.pdf. [↗](https://www-cdn.anthropic.com/)
3. Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Sergey Feldman, Mike D’arcy, et al. 2024. Openscholar: Synthesizing scientific literature with retrieval-augmented lms. arXiv preprint arXiv:2411.14199. [find](https://scholar.google.com/scholar?q=Akari+Asai%2C+Jacqueline+He%2C+Rulin+Shao%2C+Weijia+Shi%2C+Amanpreet+Singh%2C+Joseph+Chee+Chang%2C+Kyle+Lo%2C+Luca+Soldaini%2C+Sergey+Feldman%2C+Mike+D%E2%80%99arcy%2C+et+al%2E+2024%2E+Openscholar%3A+Synthesizing+scientific+literature)
4. Assafelovic. 2023. gpt-researcher. URL: [https://github.com/assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher). [↗](https://github.com/assafelovic/gpt-researcher)
5. Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, et al. 2024. [Internlm2 technical report](https://md.research.elamur.ai/free/en/papers/cai-2024-internlm2-technical-report/). arXiv preprint arXiv:2403.17297.
6. Jingqiang Chen and Hai Zhuge. 2019. Automatic generation of related work through summarizing citations. Concurrency and Computation: Practice and Experience, 31(3):e4261. [find](https://scholar.google.com/scholar?q=Jingqiang+Chen+and+Hai+Zhuge%2E+2019%2E+Automatic+generation+of+related+work+through+summarizing+citations%2E+Concurrency+and+Computation%3A+Practice+and+Experience%2C+31%283%29%3Ae4261%2E)
7. Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, et al. 2024a. [How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites](https://md.research.elamur.ai/free/en/papers/chen-2024-far-gpt-4v-closing/). arXiv preprint arXiv:2404.16821.
8. Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang, Botao Yu, Yifei Li, Zeyi Liao, Chen Wei, Zitong Lu, et al. 2024b. Scienceagentbench: Toward rigorous assessment of language agents for data-driven scientific discovery. arXiv preprint arXiv:2410.05080. [find](https://scholar.google.com/scholar?q=Ziru+Chen%2C+Shijie+Chen%2C+Yuting+Ning%2C+Qianheng+Zhang%2C+Boshi+Wang%2C+Botao+Yu%2C+Yifei+Li%2C+Zeyi+Liao%2C+Chen+Wei%2C+Zitong+Lu%2C+et+al%2E+2024b%2E+Scienceagentbench%3A+Toward+rigorous+assessment+of+language+agents+for+)
9. Clarivate. 2024. Essential science indicators: Learn the basics. URL: [https://clarivate.libguides.com/esi](https://clarivate.libguides.com/esi). [↗](https://clarivate.libguides.com/esi)
10. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. [A survey on rag meeting llms: Towards retrieval-augmented large language models](https://md.research.elamur.ai/free/en/papers/fan-2024-survey-rag-meeting-llms-towards/). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 6491– 6501.
11. 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](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). arXiv preprint arXiv:2312.10997.
12. Alireza Ghafarollahi and Markus J Buehler. 2024. Sciagents: Automating scientific discovery through multi-agent intelligent graph reasoning. arXiv preprint arXiv:2409.05556. [find](https://scholar.google.com/scholar?q=Alireza+Ghafarollahi+and+Markus+J+Buehler%2E+2024%2E+Sciagents%3A+Automating+scientific+discovery+through+multi%2Dagent+intelligent+graph+reasoning%2E+arXiv+preprint+arXiv%3A2409%2E05556%2E)
13. Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, and Alfio Gliozzo. 2022. [Re2G: Retrieve, rerank, generate](https://md.research.elamur.ai/free/en/papers/glass-2022-re2g-retrieve-rerank-generate/). In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages…
14. Cong Duy Vu Hoang and Min-Yen Kan. 2010. Towards automated related work summarization. In Coling 2010: Posters, pages 427–435. [find](https://scholar.google.com/scholar?q=Cong+Duy+Vu+Hoang+and+Min%2DYen+Kan%2E+2010%2E+Towards+automated+related+work+summarization%2E+In+Coling+2010%3A+Posters%2C+pages+427%E2%80%93435%2E)
15. Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, and Zhenzhong Lan. 2024a. Nova: An iterative planning and search approach to enhance novelty and diversity of llm generated ideas. arXiv preprint arXiv:2410.14255. [find](https://scholar.google.com/scholar?q=Xiang+Hu%2C+Hongyu+Fu%2C+Jinge+Wang%2C+Yifeng+Wang%2C+Zhikun+Li%2C+Renjun+Xu%2C+Yu+Lu%2C+Yaochu+Jin%2C+Lili+Pan%2C+and+Zhenzhong+Lan%2E+2024a%2E+Nova%3A+An+iterative+planning+and+search+approach+to+enhance+novelty+and+divers)
16. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. 2024. [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://md.research.elamur.ai/free/en/papers/lu-2024-ai-scientist-fully-automated/) . ArXiv, abs/2408.06292.
17. Haoyang Su, Renqi Chen, Shixiang Tang, Xinzhe Zheng, Jingzhe Li, Zhenfei Yin, Wanli Ouyang, and Nanqing Dong. 2024. Two heads are better than one: A multi-agent system has the potential to improve scientific idea generation. arXiv preprint arXiv:2410.09403. — [arXiv:2410.09403](https://arxiv.org/abs/2410.09403) [find](https://scholar.google.com/scholar?q=Haoyang+Su%2C+Renqi+Chen%2C+Shixiang+Tang%2C+Xinzhe+Zheng%2C+Jingzhe+Li%2C+Zhenfei+Yin%2C+Wanli+Ouyang%2C+and+Nanqing+Dong%2E+2024%2E+Two+heads+are+better+than+one%3A+A+multi%2Dagent+system+has+the+potential+to+improve+sci)
18. Yue Hu and Xiaojun Wan. 2014. Automatic generation of related work sections in scientific papers: an optimization approach. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1624–1633. [find](https://scholar.google.com/scholar?q=Yue+Hu+and+Xiaojun+Wan%2E+2014%2E+Automatic+generation+of+related+work+sections+in+scientific+papers%3A+an+optimization+approach%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Langua)
19. Xiaoping Sun and Hai Zhuge. 2019. Automatic generation of survey paper based on template tree. In 2019 15th International Conference on Semantics, Knowledge and Grids (SKG), pages 89–96. IEEE. [find](https://scholar.google.com/scholar?q=Xiaoping+Sun+and+Hai+Zhuge%2E+2019%2E+Automatic+generation+of+survey+paper+based+on+template+tree%2E+In+2019+15th+International+Conference+on+Semantics%2C+Knowledge+and+Grids+%28SKG%29%2C+pages+89%E2%80%9396%2E+IEEE%2E)
20. Yuntong Hu, Zhuofeng Li, Zheng Zhang, Chen Ling, Raasikh Kanjiani, Boxin Zhao, and Liang Zhao. 2024b. [Hireview: Hierarchical taxonomy-driven automatic literature review generation](https://md.research.elamur.ai/free/en/papers/hu-2024-taxonomy-tree-generation-citation-graph/). arXiv preprint arXiv:2410.03761.
21. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
22. Qian Huang, Jian Vora, Percy Liang, and Jure Leskovec. 2024. [Mlagentbench: Evaluating language agents on machine learning experimentation](https://md.research.elamur.ai/free/en/papers/huang-2023-mlagentbench-evaluating-language-agents/). In Forty-first International Conference on Machine Learning.
23. Rahul Jha, Catherine Finegan-Dollak, Ben King, Reed Coke, and Dragomir Radev. 2015. Content models for survey generation: a factoid-based evaluation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Langu… [find](https://scholar.google.com/scholar?q=Rahul+Jha%2C+Catherine+Finegan%2DDollak%2C+Ben+King%2C+Reed+Coke%2C+and+Dragomir+Radev%2E+2015%2E+Content+models+for+survey+generation%3A+a+factoid%2Dbased+evaluation%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+A)
24. Bin Wang, Chao Xu, Xiaomeng Zhao, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Rui Xu, Kaiwen Liu, Yuan Qu, Fukai Shang, et al. 2024a. Mineru: An open-source solution for precise document content extraction. arXiv preprint arXiv:2409.18839. [find](https://scholar.google.com/scholar?q=Bin+Wang%2C+Chao+Xu%2C+Xiaomeng+Zhao%2C+Linke+Ouyang%2C+Fan+Wu%2C+Zhiyuan+Zhao%2C+Rui+Xu%2C+Kaiwen+Liu%2C+Yuan+Qu%2C+Fukai+Shang%2C+et+al%2E+2024a%2E+Mineru%3A+An+open%2Dsource+solution+for+precise+document+content+extraction%2E+a)
25. Wenxiao Wang, Lihui Gu, Liye Zhang, Yunxiang Luo, Yi Dai, Chen Shen, Liang Xie, Binbin Lin, Xiaofei He, and Jieping Ye. 2024b. Scipip: An llm-based scientific paper idea proposer. arXiv preprint arXiv:2410.23166. — [arXiv:2410.23166](https://arxiv.org/abs/2410.23166) [find](https://scholar.google.com/scholar?q=Wenxiao+Wang%2C+Lihui+Gu%2C+Liye+Zhang%2C+Yunxiang+Luo%2C+Yi+Dai%2C+Chen+Shen%2C+Liang+Xie%2C+Binbin+Lin%2C+Xiaofei+He%2C+and+Jieping+Ye%2E+2024b%2E+Scipip%3A+An+llm%2Dbased+scientific+paper+idea+proposer%2E+arXiv+preprint+arXiv)
26. Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, and Asif Ekbal. 2024. [Can large language models unlock novel scientific research ideas?](https://md.research.elamur.ai/free/en/papers/kumar-2025-can-large-language-models-unlock/) arXiv preprint arXiv:2409.06185.
27. Yidong Wang, Qi Guo, Wenjin Yao, Hongbo Zhang, Xin Zhang, Zhen Wu, Meishan Zhang, Xinyu Dai, Min Zhang, Qingsong Wen, et al. 2024c. Autosurvey: Large language models can automatically write surveys. arXiv preprint arXiv:2406.10252. [find](https://scholar.google.com/scholar?q=Yidong+Wang%2C+Qi+Guo%2C+Wenjin+Yao%2C+Hongbo+Zhang%2C+Xin+Zhang%2C+Zhen+Wu%2C+Meishan+Zhang%2C+Xinyu+Dai%2C+Min+Zhang%2C+Qingsong+Wen%2C+et+al%2E+2024c%2E+Autosurvey%3A+Large+language+models+can+automatically+write+surveys%2E+a)
28. 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/). Advances in Neural Information Processing Systems, 33:9459–9474.
29. Renqiu Xia, Song Mao, Xiangchao Yan, Hongbin Zhou, Bo Zhang, Haoyang Peng, Jiahao Pi, Daocheng Fu, Wenjie Wu, Hancheng Ye, et al. 2024a. Docgenome: An open large-scale scientific document benchmark for training and testing multi-modal large language models. arXiv preprint arXiv:2406.11633. — [arXiv:2406.11633](https://arxiv.org/abs/2406.11633) [find](https://scholar.google.com/scholar?q=Renqiu+Xia%2C+Song+Mao%2C+Xiangchao+Yan%2C+Hongbin+Zhou%2C+Bo+Zhang%2C+Haoyang+Peng%2C+Jiahao+Pi%2C+Daocheng+Fu%2C+Wenjie+Wu%2C+Hancheng+Ye%2C+et+al%2E+2024a%2E+Docgenome%3A+An+open+large%2Dscale+scientific+document+benchmark+fo)
30. Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xinxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, et al. 2024. Chain of ideas: Revolutionizing research in novel idea development with llm agents. arXiv preprint arXiv:2410.13185. [find](https://scholar.google.com/scholar?q=Long+Li%2C+Weiwen+Xu%2C+Jiayan+Guo%2C+Ruochen+Zhao%2C+Xinxuan+Li%2C+Yuqian+Yuan%2C+Boqiang+Zhang%2C+Yuming+Jiang%2C+Yifei+Xin%2C+Ronghao+Dang%2C+et+al%2E+2024%2E+Chain+of+ideas%3A+Revolutionizing+research+in+novel+idea+develop)
31. Renqiu Xia, Bo Zhang, Hancheng Ye, Xiangchao Yan, Qi Liu, Hongbin Zhou, Zijun Chen, Min Dou, Botian Shi, Junchi Yan, et al. 2024b. Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning. arXiv preprint arXiv:2402.12185. — [arXiv:2402.12185](https://arxiv.org/abs/2402.12185) [find](https://scholar.google.com/scholar?q=Renqiu+Xia%2C+Bo+Zhang%2C+Hancheng+Ye%2C+Xiangchao+Yan%2C+Qi+Liu%2C+Hongbin+Zhou%2C+Zijun+Chen%2C+Min+Dou%2C+Botian+Shi%2C+Junchi+Yan%2C+et+al%2E+2024b%2E+Chartx+%26+chartvlm%3A+A+versatile+benchmark+and+foundation+model+for+com)
32. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. [Towards general text embeddings with multi-stage contrastive learning](https://md.research.elamur.ai/free/en/papers/li-2023-towards-general-text-embeddings-multi/). arXiv preprint arXiv:2308.03281.
33. Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighoff. 2023. [C-pack: Packaged resources to advance general chinese embedding](https://md.research.elamur.ai/free/en/papers/xiao-2023-c-pack-packed-resources/). Preprint, arXiv:2309.07597.
34. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+et+al%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E19437%2E)
35. Jiakang Yuan, Xiangchao Yan, Botian Shi, Tao Chen, Wanli Ouyang, Bo Zhang, Lei Bai, Yu Qiao, and Bowen Zhou. 2025. Dolphin: Closed-loop open-ended auto-research through thinking, practice, and feedback. arXiv preprint arXiv:2501.03916. [find](https://scholar.google.com/scholar?q=Jiakang+Yuan%2C+Xiangchao+Yan%2C+Botian+Shi%2C+Tao+Chen%2C+Wanli+Ouyang%2C+Bo+Zhang%2C+Lei+Bai%2C+Yu+Qiao%2C+and+Bowen+Zhou%2E+2025%2E+Dolphin%3A+Closed%2Dloop+open%2Dended+auto%2Dresearch+through+thinking%2C+practice%2C+and+feedbac)
36. Kun Zhu, Xiaocheng Feng, Xiachong Feng, Yingsheng Wu, and Bing Qin. 2023. Hierarchical catalogue generation for literature review: A benchmark. arXiv preprint arXiv:2304.03512. [find](https://scholar.google.com/scholar?q=Kun+Zhu%2C+Xiaocheng+Feng%2C+Xiachong+Feng%2C+Yingsheng+Wu%2C+and+Bing+Qin%2E+2023%2E+Hierarchical+catalogue+generation+for+literature+review%3A+A+benchmark%2E+arXiv+preprint+arXiv%3A2304%2E03512%2E)

*Updated 31 October 2026*