---
title: "A Survey of AI Scientists — paper by Tie et al. (2025)"
description: "\"AI Scientist\" research covers systems meant to carry out the whole research cycle on their own, from… 70 references, cited by 5 papers here."
authors: ["Guiyao Tie", "Pan Zhou", "Lichao Sun"]
year: 2025
venue: "arXiv:2510.23045"
source: "https://arxiv.org/abs/2510.23045"
doi: "10.48550/arxiv.2510.23045"
arxiv: "2510.23045"
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/tie-2025-survey-ai-scientists/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tie-2025-survey-ai-scientists/)

[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/13/) / A Survey of AI Scientists

# A Survey of AI Scientists

**Authors:** [Guiyao Tie](https://md.research.elamur.ai/free/en/authors/guiyao-tie/), [Pan Zhou](https://md.research.elamur.ai/free/en/authors/pan-zhou/) and [Lichao Sun](https://md.research.elamur.ai/free/en/authors/lichao-sun/) · **Year:** 2025 · **Venue:** arXiv:2510.23045 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2510.23045) · [PDF](https://arxiv.org/pdf/2510.23045) · [DOI 10.48550/arxiv.2510.23045](https://doi.org/10.48550/arxiv.2510.23045) · [arXiv 2510.23045](https://arxiv.org/abs/2510.23045) · [OpenAlex](https://openalex.org/W4415909452)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/tie-2025-survey-ai-scientists/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
"AI Scientist" research covers systems meant to carry out the whole research cycle on their own, from reading the literature to producing a manuscript. Work in this area has grown quickly but unevenly. Individual systems tend to cover isolated steps, target a single discipline, or use benchmarks that cannot be compared with one another. Tie, Zhou and Sun organise this scattered field into one framework. They divide autonomous research into six connected stages: reviewing prior literature, generating ideas, preparing experiments, carrying out those experiments, scientific writing, and generating the final paper. They then cross these stages with four abstraction layers to form a 4×6 classification grid. Using this grid, they map more than fifty systems released between 2022 and 2025. The mapping shows a clear historical progression, recurring architectural designs and domain applications. Most systems handle only a few stages well. The survey closes with a research agenda centred on reproducibility, calibrated uncertainty, transfer across fields and governance. It is useful as a reference map for anyone building or evaluating research-automating agents.

## Key points
- The classification grid crosses the six workflow stages with four layers (Domains, Tasks, Architectures, Capabilities). It covers 50+ systems, including Coscientist, BioPlanner, AI Scientist v1/v2, Curie, AI co-scientist, DeepScientist and freephdlabor.
- The authors identify three historical phases:
  - Foundational Modules (2022–2023)
  - Closed-Loop Integration (2024)
  - Scalable Collaboration (2025 onward)
- Typical systems are mature in only 2–3 stages. Systems built for different domains nonetheless arrive at similar stage-level designs.
- Applications are grouped into general-purpose systems, chemistry/materials, biology/biomedicine, physics/engineering, and meta-science/social science.
- The proposed open directions are:
  - reproducibility-by-design with provenance tracking
  - uncertainty quantification
  - modular composition for cross-domain transfer
  - human-AI collaboration under ethical governance
- A companion GitHub repository is available at Mr-Tieguigui/Survey-for-AI-Scientist.

*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

- [Huazhong University of Science and Technology](https://md.research.elamur.ai/free/en/universities/huazhong-university-of-science-and-technology/) — University, Wuhan, China · 64 works · 8,427 citations
- [Lehigh University](https://md.research.elamur.ai/free/en/universities/lehigh-university/) — University, Bethlehem, United States · 12 works · 1,652 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 306 works · [🎯 Information Systems and Management](https://md.research.elamur.ai/free/en/shelves/decision-sciences/information-systems-and-management/) · 96 works · [🧱 Materials Science](https://md.research.elamur.ai/free/en/shelves/materials-science/) · 58 works · [🧱 Materials Chemistry](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/) · 58 works

## Cite

Cite as: Guiyao Tie, Pan Zhou and Lichao Sun. 2025. A Survey of AI Scientists. arXiv:2510.23045.

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

```bibtex
@misc{tie2025survey,
  title = {{A Survey of AI Scientists}},
  author = {Guiyao Tie, Pan Zhou and Lichao Sun},
  year = {2025},
  doi = {10.48550/arxiv.2510.23045},
  eprint = {2510.23045},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2510.23045}
}
```

- [← previous A Collection of Question Answering Datasets for Norwegian](https://md.research.elamur.ai/free/en/papers/mikhailov-2025-collection-question-answering-datasets-norwegian/)
- [next → A Survey of Idiom Datasets for Psycholinguistic and Computational Research](https://md.research.elamur.ai/free/en/papers/flor-2025-survey-idiom-datasets-psycholinguistic-computational/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/13/)

## References

70 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Fang Liu and Demosthenes Panagiotakos. Real-world data: a brief review of the methods, applications, challenges and opportunities. BMC Medical Research Methodology, 22(1):287, 2022. [find](https://scholar.google.com/scholar?q=Fang+Liu+and+Demosthenes+Panagiotakos%2E+Real%2Dworld+data%3A+a+brief+review+of+the+methods%2C+applications%2C+challenges+and+opportunities%2E+BMC+Medical+Research+Methodology%2C+22%281%29%3A287%2C+2022%2E)
2. Bassel Almarie, Paulo EP Teixeira, Kevin Pacheco-Barrios, Carlos Augusto Rossetti, and Felipe Fregni. Editorial–the use of large language models in science: Opportunities and challenges. Principles and practice of clinical research (2015), 9(1):1, 2023. [find](https://scholar.google.com/scholar?q=Bassel+Almarie%2C+Paulo+EP+Teixeira%2C+Kevin+Pacheco%2DBarrios%2C+Carlos+Augusto+Rossetti%2C+and+Felipe+Fregni%2E+Editorial%E2%80%93the+use+of+large+language+models+in+science%3A+Opportunities+and+challenges%2E+Principles+an)
3. Sibel Erduran and Olivia Levrini. The impact of artificial intelligence on scientific practices: an emergent area of research for science education. International Journal of Science Education, 46(18):1982–1989, 2024. [find](https://scholar.google.com/scholar?q=Sibel+Erduran+and+Olivia+Levrini%2E+The+impact+of+artificial+intelligence+on+scientific+practices%3A+an+emergent+area+of+research+for+science+education%2E+International+Journal+of+Science+Education%2C+46%2818%29%3A)
4. Mourad Gridach, Jay Nanavati, Khaldoun Zine El Abidine, Lenon Mendes, and Christina Mack. Agentic ai for scientific discovery: A survey of progress, challenges, and future directions. arXiv preprint arXiv:2503.08979, 2025. — [arXiv:2503.08979](https://arxiv.org/abs/2503.08979) [find](https://scholar.google.com/scholar?q=Mourad+Gridach%2C+Jay+Nanavati%2C+Khaldoun+Zine+El+Abidine%2C+Lenon+Mendes%2C+and+Christina+Mack%2E+Agentic+ai+for+scientific+discovery%3A+A+survey+of+progress%2C+challenges%2C+and+future+directions%2E+arXiv+preprint+a)
5. Jiaqi Wei, Yuejin Yang, Xiang Zhang, Yuhan Chen, Xiang Zhuang, Zhangyang Gao, Dongzhan Zhou, Guangshuai Wang, Zhiqiang Gao, Juntai Cao, et al. [From ai for science to agentic science: A survey on autonomous scientific discovery](https://md.research.elamur.ai/free/en/papers/wei-2025-ai-science-agentic-science/). arXiv preprint arXiv:2508.14111, 2025.
6. Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Shengran Hu, Chris Lu, Jakob Foerster, Jeff Clune, and David Ha. [The ai scientist-v2: Workshop-level automated scientific discovery via agentic tree search](https://md.research.elamur.ai/free/en/papers/yamada-2025-ai-scientist-v2-workshop/). arXiv preprint arXiv:2504.08066, 2025.
7. Jack Gallifant, Amelia Fiske, Yulia A Levites Strekalova, Juan S Osorio-Valencia, Rachael Parke, Rogers Mwavu, Nicole Martinez, Judy Wawira Gichoya, Marzyeh Ghassemi, Dina Demner-Fushman, et al. Peer review of gpt-4 technical report and systems card. PLOS digital health, 3(1):e0000417, 2024. [find](https://scholar.google.com/scholar?q=Jack+Gallifant%2C+Amelia+Fiske%2C+Yulia+A+Levites+Strekalova%2C+Juan+S+Osorio%2DValencia%2C+Rachael+Parke%2C+Rogers+Mwavu%2C+Nicole+Martinez%2C+Judy+Wawira+Gichoya%2C+Marzyeh+Ghassemi%2C+Dina+Demner%2DFushman%2C+et+al%2E+Peer+)
8. Michael Schmidt and Hod Lipson. Distilling free-form natural laws from experimental data. science, 324(5923):81–85, 2009. [find](https://scholar.google.com/scholar?q=Michael+Schmidt+and+Hod+Lipson%2E+Distilling+free%2Dform+natural+laws+from+experimental+data%2E+science%2C+324%285923%29%3A81%E2%80%9385%2C+2009%2E)
9. Alireza Ghafarollahi and Markus J Buehler. Sciagents: automating scientific discovery through bioinspired multi-agent intelligent graph reasoning. Advanced Materials, 37(22):2413523, 2025. [find](https://scholar.google.com/scholar?q=Alireza+Ghafarollahi+and+Markus+J+Buehler%2E+Sciagents%3A+automating+scientific+discovery+through+bioinspired+multi%2Dagent+intelligent+graph+reasoning%2E+Advanced+Materials%2C+37%2822%29%3A2413523%2C+2025%2E)
10. Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding, Yiming Qiu, Zhenning Yang, Yibo Huang, Jayanth Srinivasa, Myungjin Lee, Mosharaf Chowdhury, and Ang Chen. [Curie: Toward rigorous and automated scientific experimentation with ai agents](https://md.research.elamur.ai/free/en/papers/kon-2025-curie-rigorous-automated-scientific/). arXiv preprint arXiv:2502.16069, 2025.
11. Odhran O’Donoghue, Aleksandar Shtedritski, John Ginger, Ralph Abboud, Ali Ghareeb, and Samuel Rodriques. Bioplanner: automatic evaluation of llms on protocol planning in biology. pages 2676–2694, 2023. [find](https://scholar.google.com/scholar?q=Odhran+O%E2%80%99Donoghue%2C+Aleksandar+Shtedritski%2C+John+Ginger%2C+Ralph+Abboud%2C+Ali+Ghareeb%2C+and+Samuel+Rodriques%2E+Bioplanner%3A+automatic+evaluation+of+llms+on+protocol+planning+in+biology%2E+pages+2676%E2%80%932694%2C+2023)
12. Pat Langley. Scientific discovery: Computational explorations of the creative processes. MIT press, 1987. [find](https://scholar.google.com/scholar?q=Pat+Langley%2E+Scientific+discovery%3A+Computational+explorations+of+the+creative+processes%2E+MIT+press%2C+1987%2E)
13. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. [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 preprint arXiv:2408.06292, 2024.
14. Yingming Pu, Tao Lin, and Hongyu Chen. Piflow: Principle-aware scientific discovery with multi-agent collaboration. arXiv preprint arXiv:2505.15047, 2025. — [arXiv:2505.15047](https://arxiv.org/abs/2505.15047) [find](https://scholar.google.com/scholar?q=Yingming+Pu%2C+Tao+Lin%2C+and+Hongyu+Chen%2E+Piflow%3A+Principle%2Daware+scientific+discovery+with+multi%2Dagent+collaboration%2E+arXiv+preprint+arXiv%3A2505%2E15047%2C+2025%2E+%E2%80%94+%5BarXiv%3A2505%2E15047%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F25)
15. Daniil A Boiko, Robert MacKnight, Ben Kline, and Gabe Gomes. [Autonomous chemical research with large language models](https://md.research.elamur.ai/free/en/papers/boiko-2023-autonomous-chemical-research-large-language/). Nature, 624(7992):570–578, 2023.
16. Tejumade Afonja, Ivaxi Sheth, Ruta Binkyte, Waqar Hanif, Thomas Ulas, Matthias Becker, and Mario Fritz. Llm4grn: Discovering causal gene regulatory networks with llms–evaluation through synthetic data generation. arXiv preprint arXiv:2410.15828, 2024. [find](https://scholar.google.com/scholar?q=Tejumade+Afonja%2C+Ivaxi+Sheth%2C+Ruta+Binkyte%2C+Waqar+Hanif%2C+Thomas+Ulas%2C+Matthias+Becker%2C+and+Mario+Fritz%2E+Llm4grn%3A+Discovering+causal+gene+regulatory+networks+with+llms%E2%80%93evaluation+through+synthetic+data)
17. Shijie Xia, Yuhan Sun, and Pengfei Liu. Sr-scientist: Scientific equation discovery with agentic ai. arXiv preprint arXiv:2510.11661, 2025. [find](https://scholar.google.com/scholar?q=Shijie+Xia%2C+Yuhan+Sun%2C+and+Pengfei+Liu%2E+Sr%2Dscientist%3A+Scientific+equation+discovery+with+agentic+ai%2E+arXiv+preprint+arXiv%3A2510%2E11661%2C+2025%2E)
18. Jiabin Tang, Lianghao Xia, Zhonghang Li, and Chao Huang. [Ai-researcher: Autonomous scientific innovation](https://md.research.elamur.ai/free/en/papers/tang-2025-ai-researcher-autonomous-scientific/). arXiv preprint arXiv:2505.18705, 2025.
19. Tingting Chen, Srinivas Anumasa, Beibei Lin, Vedant Shah, Anirudh Goyal, and Dianbo Liu. Auto-bench: An automated benchmark for scientific discovery in llms. arXiv preprint arXiv:2502.[15224, 2025](https://md.research.elamur.ai/free/en/papers/chen-2025-auto-discovery-bench-diagnosing-structured/).
20. Yujie Liu, Zonglin Yang, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, and Dongzhan Zhou. [Researchbench: Benchmarking llms in scientific discovery via inspiration-based task decomposition](https://md.research.elamur.ai/free/en/papers/liu-2025-researchbench-benchmarking-llms-scientific/). arXiv preprint arXiv:2503.21248, 2025.
21. Sikun Guo, Amir Hassan Shariatmadari, Guangzhi Xiong, Albert Huang, Myles Kim, Corey M Williams, Stefan Bekiranov, and Aidong Zhang. Ideabench: Benchmarking large language models for research idea generation. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.… [find](https://scholar.google.com/scholar?q=Sikun+Guo%2C+Amir+Hassan+Shariatmadari%2C+Guangzhi+Xiong%2C+Albert+Huang%2C+Myles+Kim%2C+Corey+M+Williams%2C+Stefan+Bekiranov%2C+and+Aidong+Zhang%2E+Ideabench%3A+Benchmarking+large+language+models+for+research+idea+gen)
22. Yangqiaoyu Zhou, Haokun Liu, Tejes Srivastava, Hongyuan Mei, and Chenhao Tan. [Hypothesis generation with large language models](https://md.research.elamur.ai/free/en/papers/zhou-2024-hypothesis-generation-large-language/). arXiv preprint arXiv:2404.04326, 2024.
23. Rosni Vasu, Chandrayee Basu, Bhavana Dalvi, Cristina Sarasua, Peter Clark, and Abraham Bernstein. [Hyper: Literature-grounded hypothesis generation and distillation with provenance](https://md.research.elamur.ai/free/en/papers/vasu-2025-hyper-literature-grounded-hypothesis-generation/). pages 25424– 25449, 2025.
24. Shubham Agarwal, Gaurav Sahu, Abhay Puri, Issam H Laradji, Krishnamurthy DJ Dvijotham, Jason Stanley, Laurent Charlin, and Christopher Pal. [Litllm: A toolkit for scientific literature review](https://md.research.elamur.ai/free/en/papers/agarwal-2024-litllm-toolkit-scientific-literature-review/). arXiv preprint arXiv:2402.01788, 2024.
25. Ziming Luo, Zonglin Yang, Zexin Xu, Wei Yang, and Xinya Du. [Llm4sr: A survey on large language models for scientific research](https://md.research.elamur.ai/free/en/papers/luo-2025-llm4sr-survey-large-language/). arXiv preprint arXiv:2501.04306, 2025.
26. Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Wen-tau Yih, Daniel Fried, Sida Wang, and Tao Yu. Ds-1000: A natural and reliable benchmark for data science code generation. In International Conference on Machine Learning, pages 18319–18345. PMLR, 2023. [find](https://scholar.google.com/scholar?q=Yuhang+Lai%2C+Chengxi+Li%2C+Yiming+Wang%2C+Tianyi+Zhang%2C+Ruiqi+Zhong%2C+Luke+Zettlemoyer%2C+Wen%2Dtau+Yih%2C+Daniel+Fried%2C+Sida+Wang%2C+and+Tao+Yu%2E+Ds%2D1000%3A+A+natural+and+reliable+benchmark+for+data+science+code+gene)
27. Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, and Jun Wang. [Ds-agent: Automated data science by empowering large language models with case-based reasoning](https://md.research.elamur.ai/free/en/papers/guo-2024-ds-agent-automated-data-science/). arXiv preprint arXiv:2402.17453, 2024.
28. Gihan Panapitiya, Emily Saldanha, Heather Job, and Olivia Hess. Autolabs: Cognitive multi-agent systems with self-correction for autonomous chemical experimentation. arXiv preprint arXiv:2509.25651, 2025. — [arXiv:2509.25651](https://arxiv.org/abs/2509.25651) [find](https://scholar.google.com/scholar?q=Gihan+Panapitiya%2C+Emily+Saldanha%2C+Heather+Job%2C+and+Olivia+Hess%2E+Autolabs%3A+Cognitive+multi%2Dagent+systems+with+self%2Dcorrection+for+autonomous+chemical+experimentation%2E+arXiv+preprint+arXiv%3A2509%2E25651%2C+2)
29. Yuning Wu, Jiahao Mei, Ming Yan, Chenliang Li, Shaopeng Lai, Yuran Ren, Zijia Wang, Ji Zhang, Mengyue Wu, Qin Jin, et al. Writingbench: A comprehensive benchmark for generative writing. arXiv preprint arXiv:2503.05244, 2025. — [arXiv:2503.05244](https://arxiv.org/abs/2503.05244) [find](https://scholar.google.com/scholar?q=Yuning+Wu%2C+Jiahao+Mei%2C+Ming+Yan%2C+Chenliang+Li%2C+Shaopeng+Lai%2C+Yuran+Ren%2C+Zijia+Wang%2C+Ji+Zhang%2C+Mengyue+Wu%2C+Qin+Jin%2C+et+al%2E+Writingbench%3A+A+comprehensive+benchmark+for+generative+writing%2E+arXiv+preprint)
30. Qian Huang, Jian Vora, Percy Liang, and Jure Leskovec. [Mlagentbench: Evaluating language agents on machine learning experimentation](https://md.research.elamur.ai/free/en/papers/huang-2023-mlagentbench-evaluating-language-agents/). arXiv preprint arXiv:2310.03302, 2023.
31. Shuxiang Cao, Zijian Zhang, Mohammed Alghadeer, Simone D. Fasciati, Michele Piscitelli, Mustafa Bakr, and Peter Leek. Agents for self-driving laboratories applied to quantum computing. arXiv preprint arXiv:2412.07978, 2024. — [arXiv:2412.07978](https://arxiv.org/abs/2412.07978) [find](https://scholar.google.com/scholar?q=Shuxiang+Cao%2C+Zijian+Zhang%2C+Mohammed+Alghadeer%2C+Simone+D%2E+Fasciati%2C+Michele+Piscitelli%2C+Mustafa+Bakr%2C+and+Peter+Leek%2E+Agents+for+self%2Ddriving+laboratories+applied+to+quantum+computing%2E+arXiv+preprint+)
32. Juraj Gottweis, Wei-Hung Weng, Alexander Daryin, Tao Tu, Anil Palepu, Petar Sirkovic, Artiom Myaskovsky, Felix Weissenberger, Keran Rong, Ryutaro Tanno, et al. Towards an ai co-scientist. arXiv preprint arXiv:2502.[18864, 2025](https://md.research.elamur.ai/free/en/papers/gottweis-2025-accelerating-scientific-discovery-co/).
33. Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, and Pengfei Liu. [Deepresearcher: Scaling deep research via reinforcement learning in real-world environments](https://md.research.elamur.ai/free/en/papers/zheng-2025-deepresearcher-scaling-deep-research-reinforcement/). arXiv preprint arXiv:2504.03160, 2025.
34. Patrick Tser Jern Kon, Jiachen Liu, Xinyi Zhu, Qiuyi Ding, Jingjia Peng, Jiarong Xing, Yibo Huang, Yiming Qiu, Jayanth Srinivasa, Myungjin Lee, et al. [Exp-bench: Can ai conduct ai research experiments?](https://md.research.elamur.ai/free/en/papers/kon-2025-exp-bench-ai-conduct/) arXiv preprint arXiv:2505.24785, 2025.
35. Yixin Liu, Yonghui Wu, Denghui Zhang, and Lichao Sun. Agentic autosurvey: Let llms survey llms. arXiv preprint arXiv:2509.18661, 2025. — [arXiv:2509.18661](https://arxiv.org/abs/2509.18661) [find](https://scholar.google.com/scholar?q=Yixin+Liu%2C+Yonghui+Wu%2C+Denghui+Zhang%2C+and+Lichao+Sun%2E+Agentic+autosurvey%3A+Let+llms+survey+llms%2E+arXiv+preprint+arXiv%3A2509%2E18661%2C+2025%2E+%E2%80%94+%5BarXiv%3A2509%2E18661%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2509%2E18661%29)
36. Yixuan Weng, Minjun Zhu, Qiujie Xie, Qiyao Sun, Zhen Lin, Sifan Liu, and Yue Zhang. [Deepscientist: Advancing frontier-pushing scientific findings progressively](https://md.research.elamur.ai/free/en/papers/weng-2025-deepscientist-advancing-frontier-pushing/). arXiv preprint arXiv:2509.26603, 2025.
37. Ed Li, Junyu Ren, Xintian Pan, Cat Yan, Chuanhao Li, Dirk Bergemann, and Zhuoran Yang. Build your personalized research group: A multiagent framework for continual and interactive science automation. arXiv preprint arXiv:2510.15624, 2025. — [arXiv:2510.15624](https://arxiv.org/abs/2510.15624) [find](https://scholar.google.com/scholar?q=Ed+Li%2C+Junyu+Ren%2C+Xintian+Pan%2C+Cat+Yan%2C+Chuanhao+Li%2C+Dirk+Bergemann%2C+and+Zhuoran+Yang%2E+Build+your+personalized+research+group%3A+A+multiagent+framework+for+continual+and+interactive+science+automation%2E+)
38. Nathan J Szymanski, Bernardus Rendy, Yuxing Fei, Rishi E Kumar, Tanjin He, David Milsted, Matthew J McDermott, Max Gallant, Ekin Dogus Cubuk, Amil Merchant, et al. An autonomous laboratory for the accelerated synthesis of novel materials. Nature, 624(7990):86–91, 2023. [find](https://scholar.google.com/scholar?q=Nathan+J+Szymanski%2C+Bernardus+Rendy%2C+Yuxing+Fei%2C+Rishi+E+Kumar%2C+Tanjin+He%2C+David+Milsted%2C+Matthew+J+McDermott%2C+Max+Gallant%2C+Ekin+Dogus+Cubuk%2C+Amil+Merchant%2C+et+al%2E+An+autonomous+laboratory+for+the+acc)
39. Kyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney, and Daniel S Weld. [S2orc: The semantic scholar open research corpus](https://md.research.elamur.ai/free/en/papers/lo-2019-s2orc-semantic-scholar-open-research/). pages 4969–4983, 2020.
40. Jakub Lála, Odhran O’Donoghue, Aleksandar Shtedritski, Sam Cox, Samuel G Rodriques, and Andrew D White. [Paperqa: Retrieval-augmented generative agent for scientific research](https://md.research.elamur.ai/free/en/papers/lala-2023-paperqa-retrieval-augmented-generative/). arXiv preprint arXiv:2312.07559, 2023.
41. Zheye Deng, Chunkit Chan, Weiqi Wang, Yuxi Sun, Wei Fan, Tianshi Zheng, Yauwai Yim, and Yangqiu Song. Text-tuple-table: Towards information integration in text-to-table generation via global tuple extraction. arXiv preprint arXiv:2404.14215, 2024. [find](https://scholar.google.com/scholar?q=Zheye+Deng%2C+Chunkit+Chan%2C+Weiqi+Wang%2C+Yuxi+Sun%2C+Wei+Fan%2C+Tianshi+Zheng%2C+Yauwai+Yim%2C+and+Yangqiu+Song%2E+Text%2Dtuple%2Dtable%3A+Towards+information+integration+in+text%2Dto%2Dtable+generation+via+global+tuple+ext)
42. Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, et al. [Many heads are better than one: Improved scientific idea generation by a llm-based multi-agent system](https://md.research.elamur.ai/free/en/papers/su-2025-many-heads-are-better-than/). arXiv preprint arXiv:2410.09403, 2024.
43. Xianjie Wu, Jian Yang, Linzheng Chai, Ge Zhang, Jiaheng Liu, Xeron Du, Di Liang, Daixin Shu, Xianfu Cheng, Tianzhen Sun, et al. Tablebench: A comprehensive and complex benchmark for table question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 25497– 25… [find](https://scholar.google.com/scholar?q=Xianjie+Wu%2C+Jian+Yang%2C+Linzheng+Chai%2C+Ge+Zhang%2C+Jiaheng+Liu%2C+Xeron+Du%2C+Di+Liang%2C+Daixin+Shu%2C+Xianfu+Cheng%2C+Tianzhen+Sun%2C+et+al%2E+Tablebench%3A+A+comprehensive+and+complex+benchmark+for+table+question+ans)
44. Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, Bhavana Dalvi Mishra, Abhijeetsingh Meena, Aryan Prakhar, Tirth Vora, Tushar Khot, Ashish Sabharwal, and Peter Clark. [Discoverybench: Towards data-driven discovery with large language models](https://md.research.elamur.ai/free/en/papers/majumder-2024-discoverybench-data-driven-discovery/). arXiv preprint arXiv:2407.01725, 2024.
45. Ken Gu, Ruoxi Shang, Ruien Jiang, Keying Kuang, Richard-John Lin, Donghe Lyu, Yue Mao, Youran Pan, Teng Wu, Jiaqian Yu, et al. Blade: Benchmarking language model agents for data-driven science. arXiv preprint arXiv:2408.09667, 2024. [find](https://scholar.google.com/scholar?q=Ken+Gu%2C+Ruoxi+Shang%2C+Ruien+Jiang%2C+Keying+Kuang%2C+Richard%2DJohn+Lin%2C+Donghe+Lyu%2C+Yue+Mao%2C+Youran+Pan%2C+Teng+Wu%2C+Jiaqian+Yu%2C+et+al%2E+Blade%3A+Benchmarking+language+model+agents+for+data%2Ddriven+science%2E+arXiv+)
46. Indrajeet Mandal, Jitendra Soni, Mohd Zaki, Morten M Smedskjaer, Katrin Wondraczek, Lothar Wondraczek, Nitya Nand Gosvami, and NM Anoop Krishnan. Evaluating large language model agents for automation of atomic force microscopy. Nature Communications, 16(1):9104, 2025. [find](https://scholar.google.com/scholar?q=Indrajeet+Mandal%2C+Jitendra+Soni%2C+Mohd+Zaki%2C+Morten+M+Smedskjaer%2C+Katrin+Wondraczek%2C+Lothar+Wondraczek%2C+Nitya+Nand+Gosvami%2C+and+NM+Anoop+Krishnan%2E+Evaluating+large+language+model+agents+for+automation+)
47. Yu-Zhe Shi, Mingchen Liu, Fanxu Meng, Qiao Xu, Zhangqian Bi, Kun He, Lecheng Ruan, and Qining Wang. Hierarchically encapsulated representation for protocol design in self-driving labs. arXiv preprint arXiv:2504.03810, 2025. — [arXiv:2504.03810](https://arxiv.org/abs/2504.03810) [find](https://scholar.google.com/scholar?q=Yu%2DZhe+Shi%2C+Mingchen+Liu%2C+Fanxu+Meng%2C+Qiao+Xu%2C+Zhangqian+Bi%2C+Kun+He%2C+Lecheng+Ruan%2C+and+Qining+Wang%2E+Hierarchically+encapsulated+representation+for+protocol+design+in+self%2Ddriving+labs%2E+arXiv+preprint+)
48. Alexander V Tobias and Adam Wahab. Autonomous ‘self-driving’laboratories: a review of technology and policy implications. Royal Society Open Science, 12(7):250646, 2025. [find](https://scholar.google.com/scholar?q=Alexander+V+Tobias+and+Adam+Wahab%2E+Autonomous+%E2%80%98self%2Ddriving%E2%80%99laboratories%3A+a+review+of+technology+and+policy+implications%2E+Royal+Society+Open+Science%2C+12%287%29%3A250646%2C+2025%2E)
49. Kourosh Darvish, Marta Skreta, Yuchi Zhao, Naruki Yoshikawa, Sagnik Som, Miroslav Bogdanovic, Yang Cao, Han Hao, Haoping Xu, Alán Aspuru-Guzik, et al. Organa: A robotic assistant for automated chemistry experimentation and characterization. Matter, 8(2), 2025. [find](https://scholar.google.com/scholar?q=Kourosh+Darvish%2C+Marta+Skreta%2C+Yuchi+Zhao%2C+Naruki+Yoshikawa%2C+Sagnik+Som%2C+Miroslav+Bogdanovic%2C+Yang+Cao%2C+Han+Hao%2C+Haoping+Xu%2C+Al%C3%A1n+Aspuru%2DGuzik%2C+et+al%2E+Organa%3A+A+robotic+assistant+for+automated+chemist)
50. Pengcheng Yin, Wen-Ding Li, Kefan Xiao, Abhishek Rao, Yeming Wen, Kensen Shi, Joshua Howland, Paige Bailey, Michele Catasta, Henryk Michalewski, et al. [Natural language to code generation in interactive data science notebooks](https://md.research.elamur.ai/free/en/papers/yin-2023-natural-language-code-generation-interactive/). pages 126–173, 2023.
51. Jiakun Li, Hui Zong, Erman Wu, Rongrong Wu, Zhufeng Peng, Jing Zhao, Lu Yang, Hong Xie, and Bairong Shen. Exploring the potential of artificial intelligence to enhance the writing of english academic papers by non-native english-speaking medical students-the educational application of chatgpt. BMC M… [find](https://scholar.google.com/scholar?q=Jiakun+Li%2C+Hui+Zong%2C+Erman+Wu%2C+Rongrong+Wu%2C+Zhufeng+Peng%2C+Jing+Zhao%2C+Lu+Yang%2C+Hong+Xie%2C+and+Bairong+Shen%2E+Exploring+the+potential+of+artificial+intelligence+to+enhance+the+writing+of+english+academic+)
52. Adam Cheng, Aaron Calhoun, and Gabriel Reedy. Artificial intelligence-assisted academic writing: recommendations for ethical use. Advances in Simulation, 10(1):22, 2025. [find](https://scholar.google.com/scholar?q=Adam+Cheng%2C+Aaron+Calhoun%2C+and+Gabriel+Reedy%2E+Artificial+intelligence%2Dassisted+academic+writing%3A+recommendations+for+ethical+use%2E+Advances+in+Simulation%2C+10%281%29%3A22%2C+2025%2E)
53. Amalio Telenti, Michael Auli, Brian L Hie, Cyrus Maher, Suchi Saria, and John PA Ioannidis. Large language models for science and medicine. European journal of clinical investigation, 54(6):e14183, 2024. [find](https://scholar.google.com/scholar?q=Amalio+Telenti%2C+Michael+Auli%2C+Brian+L+Hie%2C+Cyrus+Maher%2C+Suchi+Saria%2C+and+John+PA+Ioannidis%2E+Large+language+models+for+science+and+medicine%2E+European+journal+of+clinical+investigation%2C+54%286%29%3Ae14183%2C+20)
54. Mohamed Khalifa and Mona Albadawy. Using artificial intelligence in academic writing and research: An essential productivity tool. Computer Methods and Programs in Biomedicine Update, 5:100145, 2024. [find](https://scholar.google.com/scholar?q=Mohamed+Khalifa+and+Mona+Albadawy%2E+Using+artificial+intelligence+in+academic+writing+and+research%3A+An+essential+productivity+tool%2E+Computer+Methods+and+Programs+in+Biomedicine+Update%2C+5%3A100145%2C+2024%2E)
55. Hui Guo and Syaza Hazwani Zaini. Artificial intelligence in academic writing: A literature review. Asian Pendidikan, 4(2):46–55, 2024. [find](https://scholar.google.com/scholar?q=Hui+Guo+and+Syaza+Hazwani+Zaini%2E+Artificial+intelligence+in+academic+writing%3A+A+literature+review%2E+Asian+Pendidikan%2C+4%282%29%3A46%E2%80%9355%2C+2024%2E)
56. Michele Salvagno, Fabio Silvio Taccone, and Alberto Giovanni Gerli. Can artificial intelligence help for scientific writing? Critical care, 27(1):75, 2023. [find](https://scholar.google.com/scholar?q=Michele+Salvagno%2C+Fabio+Silvio+Taccone%2C+and+Alberto+Giovanni+Gerli%2E+Can+artificial+intelligence+help+for+scientific+writing%3F+Critical+care%2C+27%281%29%3A75%2C+2023%2E)
57. Guijin Son, Jiwoo Hong, Honglu Fan, Heejeong Nam, Hyunwoo Ko, Seungwon Lim, Jinyeop Song, Jinha Choi, Gonçalo Paulo, Youngjae Yu, et al. [When ai co-scientists fail: Spot-a benchmark for automated verification of scientific research](https://md.research.elamur.ai/free/en/papers/son-2025-ai-co-scientists-fail/). arXiv preprint arXiv:2505.11855, 2025.
58. Li Zhou, Ruijie Zhang, Xunlian Dai, Daniel Hershcovich, and Haizhou Li. Large language models penetration in scholarly writing and peer review. arXiv preprint arXiv:2502.11193, 2025. — [arXiv:2502.11193](https://arxiv.org/abs/2502.11193) [find](https://scholar.google.com/scholar?q=Li+Zhou%2C+Ruijie+Zhang%2C+Xunlian+Dai%2C+Daniel+Hershcovich%2C+and+Haizhou+Li%2E+Large+language+models+penetration+in+scholarly+writing+and+peer+review%2E+arXiv+preprint+arXiv%3A2502%2E11193%2C+2025%2E+%E2%80%94+%5BarXiv%3A2502%2E111)
59. Maryam Feyzollahi and Nima Rafizadeh. The adoption of large language models in economics research. Economics Letters, 250:112265, 2025. [find](https://scholar.google.com/scholar?q=Maryam+Feyzollahi+and+Nima+Rafizadeh%2E+The+adoption+of+large+language+models+in+economics+research%2E+Economics+Letters%2C+250%3A112265%2C+2025%2E)
60. Navneet Ateriya, Nagendra Singh Sonwani, Kishor Singh Thakur, Arvind Kumar, and Satish Kumar Verma. Exploring the ethical landscape of ai in academic writing. Egyptian Journal of Forensic Sciences, 15(1):36, 2025. [find](https://scholar.google.com/scholar?q=Navneet+Ateriya%2C+Nagendra+Singh+Sonwani%2C+Kishor+Singh+Thakur%2C+Arvind+Kumar%2C+and+Satish+Kumar+Verma%2E+Exploring+the+ethical+landscape+of+ai+in+academic+writing%2E+Egyptian+Journal+of+Forensic+Sciences%2C+15)
61. David B Resnik and Mohammad Hosseini. The ethics of using artificial intelligence in scientific research: new guidance needed for a new tool. AI and Ethics, 5(2):1499–1521, 2025. [find](https://scholar.google.com/scholar?q=David+B+Resnik+and+Mohammad+Hosseini%2E+The+ethics+of+using+artificial+intelligence+in+scientific+research%3A+new+guidance+needed+for+a+new+tool%2E+AI+and+Ethics%2C+5%282%29%3A1499%E2%80%931521%2C+2025%2E)
62. Kelvin Mwita. The use of artificial intelligence in academic writing: What is ethical and what is not. Available at SSRN 5243488, 2024. [find](https://scholar.google.com/scholar?q=Kelvin+Mwita%2E+The+use+of+artificial+intelligence+in+academic+writing%3A+What+is+ethical+and+what+is+not%2E+Available+at+SSRN+5243488%2C+2024%2E)
63. Jasper Roe, Willy A Renandya, and George M Jacobs. A review of ai-powered writing tools and their implications for academic integrity in the language classroom. Journal of English and Applied Linguistics, 2(1):3, 2023. [find](https://scholar.google.com/scholar?q=Jasper+Roe%2C+Willy+A+Renandya%2C+and+George+M+Jacobs%2E+A+review+of+ai%2Dpowered+writing+tools+and+their+implications+for+academic+integrity+in+the+language+classroom%2E+Journal+of+English+and+Applied+Linguist)
64. A Jo. The promise and peril of generative ai. Nature, 614(1):214–216, 2023. [find](https://scholar.google.com/scholar?q=A+Jo%2E+The+promise+and+peril+of+generative+ai%2E+Nature%2C+614%281%29%3A214%E2%80%93216%2C+2023%2E)
65. Zijun Liu, Kaiming Liu, Yiqi Zhu, Xuanyu Lei, Zonghan Yang, Zhenhe Zhang, Peng Li, and Yang Liu. Aigs: Generating science from ai-powered automated falsification. arXiv preprint arXiv:2411.11910, 2024. — [arXiv:2411.11910](https://arxiv.org/abs/2411.11910) [find](https://scholar.google.com/scholar?q=Zijun+Liu%2C+Kaiming+Liu%2C+Yiqi+Zhu%2C+Xuanyu+Lei%2C+Zonghan+Yang%2C+Zhenhe+Zhang%2C+Peng+Li%2C+and+Yang+Liu%2E+Aigs%3A+Generating+science+from+ai%2Dpowered+automated+falsification%2E+arXiv+preprint+arXiv%3A2411%2E11910%2C+2024)
66. Erzhuo Shao, Yifang Wang, Yifan Qian, Zhenyu Pan, Han Liu, and Dashun Wang. Sciscigpt: advancing human–ai collaboration in the science of science. Nature Computational Science, pages 1–15, 2025. [find](https://scholar.google.com/scholar?q=Erzhuo+Shao%2C+Yifang+Wang%2C+Yifan+Qian%2C+Zhenyu+Pan%2C+Han+Liu%2C+and+Dashun+Wang%2E+Sciscigpt%3A+advancing+human%E2%80%93ai+collaboration+in+the+science+of+science%2E+Nature+Computational+Science%2C+pages+1%E2%80%9315%2C+2025%2E)
67. Mitra Madanchian and Hamed Taherdoost. Ai-powered innovations in high-tech research and development: From theory to practice. Computers, Materials & Continua, 81(2), 2024. [find](https://scholar.google.com/scholar?q=Mitra+Madanchian+and+Hamed+Taherdoost%2E+Ai%2Dpowered+innovations+in+high%2Dtech+research+and+development%3A+From+theory+to+practice%2E+Computers%2C+Materials+%26+Continua%2C+81%282%29%2C+2024%2E)
68. Tao Song, Man Luo, Xiaolong Zhang, Linjiang Chen, Yan Huang, Jiaqi Cao, Qing Zhu, Daobin Liu, Baicheng Zhang, Gang Zou, et al. A multiagent-driven robotic ai chemist enabling autonomous chemical research on demand. Journal of the American Chemical Society, 147(15):12534–12545, 2025. [find](https://scholar.google.com/scholar?q=Tao+Song%2C+Man+Luo%2C+Xiaolong+Zhang%2C+Linjiang+Chen%2C+Yan+Huang%2C+Jiaqi+Cao%2C+Qing+Zhu%2C+Daobin+Liu%2C+Baicheng+Zhang%2C+Gang+Zou%2C+et+al%2E+A+multiagent%2Ddriven+robotic+ai+chemist+enabling+autonomous+chemical+resea)
69. Silviu-Marian Udrescu and Max Tegmark. [Ai feynman: A physics-inspired method for symbolic regression](https://md.research.elamur.ai/free/en/papers/udrescu-2019-ai-feynman-physics-inspired/). Science advances, 6(16):eaay2631, 2020.
70. Ruoxi Xu, Yingfei Sun, Mengjie Ren, Shiguang Guo, Ruotong Pan, Hongyu Lin, Le Sun, and Xianpei Han. Ai for social science and social science of ai: A survey. Information Processing & Management, 61(3):103665, 2024. [find](https://scholar.google.com/scholar?q=Ruoxi+Xu%2C+Yingfei+Sun%2C+Mengjie+Ren%2C+Shiguang+Guo%2C+Ruotong+Pan%2C+Hongyu+Lin%2C+Le+Sun%2C+and+Xianpei+Han%2E+Ai+for+social+science+and+social+science+of+ai%3A+A+survey%2E+Information+Processing+%26+Management%2C+61%283%29)

*Updated 3 November 2026*