---
title: "Dolphin — paper by Yuan et al. (2025) — summary and ideas"
description: "It then proposes ideas and discards redundant or non-novel ones. 53 references, cited by 18 papers here."
authors: ["Jiakang Yuan", "Xiangchao Yan", "Shiyang Feng", "Bo Zhang", "Tao Chen", "Botian Shi", "Wanli Ouyang", "Yu Qiao", "Lei Bai", "Bowen Zhou"]
year: 2025
venue: "arXiv:2501.03916"
source: "https://arxiv.org/abs/2501.03916"
doi: "10.48550/arxiv.2501.03916"
arxiv: "2501.03916"
licence: "arXiv non-exclusive distribution license"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yuan-2025-dolphin-moving-closed-loop/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yuan-2025-dolphin-moving-closed-loop/)

[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/6/) / Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback

# Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback

**Authors:** [Jiakang Yuan](https://md.research.elamur.ai/free/en/authors/jiakang-yuan/), [Xiangchao Yan](https://md.research.elamur.ai/free/en/authors/xiangchao-yan/), [Shiyang Feng](https://md.research.elamur.ai/free/en/authors/shiyang-feng/), [Bo Zhang](https://md.research.elamur.ai/free/en/authors/bo-zhang/), [Tao Chen](https://md.research.elamur.ai/free/en/authors/tao-chen/), [Botian Shi](https://md.research.elamur.ai/free/en/authors/botian-shi/), [Wanli Ouyang](https://md.research.elamur.ai/free/en/authors/wanli-ouyang/), [Yu Qiao](https://md.research.elamur.ai/free/en/authors/yu-qiao/), [Lei Bai](https://md.research.elamur.ai/free/en/authors/lei-bai/) and [Bowen Zhou](https://md.research.elamur.ai/free/en/authors/bowen-zhou/) · **Year:** 2025 · **Venue:** arXiv:2501.03916 · **Licence:** [arXiv non-exclusive distribution license](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2501.03916) · [PDF](https://arxiv.org/pdf/2501.03916) · [DOI 10.48550/arxiv.2501.03916](https://doi.org/10.48550/arxiv.2501.03916) · [arXiv 2501.03916](https://arxiv.org/abs/2501.03916) · [OpenAlex](https://openalex.org/W4406192744)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [18](https://md.research.elamur.ai/free/en/papers/yuan-2025-dolphin-moving-closed-loop/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Fully automated scientific research is still out of reach. Earlier systems mostly judge LLM-generated ideas by their apparent novelty, test them on toy datasets, or never use experimental outcomes to improve later ideas. Dolphin addresses this with a closed research loop of three stages: idea generation, experimental verification and results feedback. It retrieves papers on an input topic and ranks them by topic relevance and task attributes. It then proposes ideas and discards redundant or non-novel ones. For each remaining idea, it writes an experiment plan and code, and fixes failing code by examining the local code structure linked to the error traceback. Finally, it analyses the results and feeds them into the next round. Over successive loops on public benchmarks (ModelNet40, CIFAR-100, SST-2), the share of ideas that beat baselines grew. One auto-generated 3D classification method came close to the human-designed state of the art. This shows that grounding idea quality in real experiments can make automated research measurably productive.

## Key points
- **Two efficiency mechanisms:** task-attribute-guided paper ranking improves the input papers, and exception-traceback-guided debugging raises the rate of successful code execution.
- **Idea filtering:**
  - Ideas are embedded from their summaries and compared by cosine similarity against an idea bank, which also holds earlier ineffective ideas. Any idea with a similarity above 0.8 is dropped.
  - A novelty check follows, borrowed from AI-Scientist.
- **Results and baselines:**
  - Baselines were PointNet, WideResNet and BERT-base.
  - The share of ideas that improved performance rose from 2/7 in Loop 1 to 4/8 in Loop 3, with slightly higher cost per loop.
  - The generated PointNet-CSR rivals the 3D point classification SoTA with a simpler, faster design.
- **MLE-bench:** experiments on a subset of MLE-bench show that Dolphin can plug into code-generation pipelines such as AIDE.
- **Limitations:**
  - Idea generation uses only paper titles and abstracts.
  - LLM prior knowledge may leak into the generated ideas.
  - Project-level code remains beyond the system's capabilities.

*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

- [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/) — University, Shanghai, China · 213 works · 22,907 citations

📚 Shelves (5): [🖥️ 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,888 works

## Cite

Cite as: Jiakang Yuan, Xiangchao Yan, Shiyang Feng, Bo Zhang, Tao Chen, Botian Shi, Wanli Ouyang, Yu Qiao, Lei Bai and Bowen Zhou. 2025. Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback. arXiv:2501.03916.

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

```bibtex
@misc{yuan2025dolphin,
  title = {{Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback}},
  author = {Jiakang Yuan, Xiangchao Yan, Shiyang Feng, Bo Zhang, Tao Chen, Botian Shi, Wanli Ouyang, Yu Qiao, Lei Bai and Bowen Zhou},
  year = {2025},
  doi = {10.48550/arxiv.2501.03916},
  eprint = {2501.03916},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2501.03916}
}
```

- [← previous ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning](https://md.research.elamur.ai/free/en/papers/qiao-2025-concise-confidence-guided-compression-step/)
- [next → FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation](https://md.research.elamur.ai/free/en/papers/luo-2025-finmme-benchmark-dataset-financial-multi/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

53 references, 26 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/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf](https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf). [↗](https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf)
3. Assafelovic. 2023. gpt-researcher. URL: [https://github.com/assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher). [↗](https://github.com/assafelovic/gpt-researcher)
4. Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu, Leon Maksin, Tejal Patwardhan, et al. 2024. [Mle-bench: Evaluating machine learning agents on machine learning engineering](https://md.research.elamur.ai/free/en/papers/chan-2024-mle-bench-evaluating-machine/). arXiv preprint arXiv:2410.07095.
5. Angelica Chen, David Dohan, and David So. 2024. Evoprompting: language models for code-level neural architecture search. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Angelica+Chen%2C+David+Dohan%2C+and+David+So%2E+2024%2E+Evoprompting%3A+language+models+for+code%2Dlevel+neural+architecture+search%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%2E)
6. Kang Chen, Tao Han, Junchao Gong, Lei Bai, Fenghua Ling, Jing-Jia Luo, Xi Chen, Leiming Ma, Tianning Zhang, Rui Su, et al. 2023. Fengwu: Pushing the skillful global medium-range weather forecast beyond 10 days lead. arXiv preprint arXiv:2304.02948. [find](https://scholar.google.com/scholar?q=Kang+Chen%2C+Tao+Han%2C+Junchao+Gong%2C+Lei+Bai%2C+Fenghua+Ling%2C+Jing%2DJia+Luo%2C+Xi+Chen%2C+Leiming+Ma%2C+Tianning+Zhang%2C+Rui+Su%2C+et+al%2E+2023%2E+Fengwu%3A+Pushing+the+skillful+global+medium%2Drange+weather+forecast+beyon)
7. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pages 4171–4186.
8. Yuxiang Wu Dominik Schmidt, Zhengyao Jiang. 2024. Aide. URL: [https://www.weco.ai/blog/technical-report](https://www.weco.ai/blog/technical-report). [↗](https://www.weco.ai/blog/technical-report)
9. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. [An image is worth 16x16 words: Transformers for image recognition at scale](https://md.research.elamur.ai/free/en/papers/dosovitskiy-2020-image-worth-16x16-words-transformers/). In International Conference on Learni…
10. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
11. Tao Han, Zhenghao Chen, Song Guo, Wanghan Xu, and Lei Bai. 2024. Cra5: Extreme compression of era5 for portable global climate and weather research via an efficient variational transformer. arXiv preprint arXiv:2405.03376. — [arXiv:2405.03376](https://arxiv.org/abs/2405.03376) [find](https://scholar.google.com/scholar?q=Tao+Han%2C+Zhenghao+Chen%2C+Song+Guo%2C+Wanghan+Xu%2C+and+Lei+Bai%2E+2024%2E+Cra5%3A+Extreme+compression+of+era5+for+portable+global+climate+and+weather+research+via+an+efficient+variational+transformer%2E+arXiv+prep)
12. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. [Deep residual learning for image recognition](https://md.research.elamur.ai/free/en/papers/he-2015-deep-residual-learning-image-recognition/). In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770– 778.
13. Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, and Zhenzhong Lan. 2024. [Nova: An iterative planning and search approach to enhance novelty and diversity of llm generated ideas](https://md.research.elamur.ai/free/en/papers/hu-2024-nova-iterative-planning-search-approach/). arXiv preprint arXiv:2410.14255.
14. John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, et al. 2021. [Highly accurate protein structure prediction with alphafold](https://md.research.elamur.ai/free/en/papers/jumper-2021-highly-accurate-protein-structure-prediction/). nature, 596(7873):583–589.
15. Alex Krizhevsky, Geoffrey Hinton, et al. 2009. Learning multiple layers of features from tiny images. [find](https://scholar.google.com/scholar?q=Alex+Krizhevsky%2C+Geoffrey+Hinton%2C+et+al%2E+2009%2E+Learning+multiple+layers+of+features+from+tiny+images%2E)
16. 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](https://md.research.elamur.ai/free/en/papers/li-2024-chain-ideas-revolutionizing-research/). arXiv preprint arXiv:2410.13185.
17. Siyi Liu, Chen Gao, and Yong Li. 2024. Large language model agent for hyper-parameter optimization. arXiv preprint arXiv:2402.01881. [find](https://scholar.google.com/scholar?q=Siyi+Liu%2C+Chen+Gao%2C+and+Yong+Li%2E+2024%2E+Large+language+model+agent+for+hyper%2Dparameter+optimization%2E+arXiv+preprint+arXiv%3A2402%2E01881%2E)
18. Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, and Saining Xie. 2022. A convnet for the 2020s. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11976–11986. [find](https://scholar.google.com/scholar?q=Zhuang+Liu%2C+Hanzi+Mao%2C+Chao%2DYuan+Wu%2C+Christoph+Feichtenhofer%2C+Trevor+Darrell%2C+and+Saining+Xie%2E+2022%2E+A+convnet+for+the+2020s%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+r)
19. 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.
20. Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, and Tie-Yan Liu. 2022. Biogpt: generative pre-trained transformer for biomedical text generation and mining. Briefings in bioinformatics, 23(6):bbac409. [find](https://scholar.google.com/scholar?q=Renqian+Luo%2C+Liai+Sun%2C+Yingce+Xia%2C+Tao+Qin%2C+Sheng+Zhang%2C+Hoifung+Poon%2C+and+Tie%2DYan+Liu%2E+2022%2E+Biogpt%3A+generative+pre%2Dtrained+transformer+for+biomedical+text+generation+and+mining%2E+Briefings+in+bioinfo)
21. OpenAI. 2024. Hello gpt-4o. [https://openai.com/index/hello-gpt-4o/](https://openai.com/index/hello-gpt-4o/). [↗](https://openai.com/index/hello-gpt-4o/)
22. Biqing Qi, Kaiyan Zhang, Haoxiang Li, Kai Tian, Sihang Zeng, Zhang-Ren Chen, and Bowen Zhou. 2023. [Large language models are zero shot hypothesis proposers](https://md.research.elamur.ai/free/en/papers/qi-2023-large-language-models-zero-shot/). arXiv preprint arXiv:2311.05965.
23. Biqing Qi, Kaiyan Zhang, Kai Tian, Haoxiang Li, Zhang-Ren Chen, Sihang Zeng, Ermo Hua, Hu Jinfang, and Bowen Zhou. 2024. [Large language models as biomedical hypothesis generators: A comprehensive evaluation](https://md.research.elamur.ai/free/en/papers/qi-2024-large-language-models-biomedical-hypothesis/). arXiv preprint arXiv:2407.08940.
24. Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017a. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660. [find](https://scholar.google.com/scholar?q=Charles+R+Qi%2C+Hao+Su%2C+Kaichun+Mo%2C+and+Leonidas+J+Guibas%2E+2017a%2E+Pointnet%3A+Deep+learning+on+point+sets+for+3d+classification+and+segmentation%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+a)
25. Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017b. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Charles+Ruizhongtai+Qi%2C+Li+Yi%2C+Hao+Su%2C+and+Leonidas+J+Guibas%2E+2017b%2E+Pointnet%2B%2B%3A+Deep+hierarchical+feature+learning+on+point+sets+in+a+metric+space%2E+Advances+in+neural+information+processing+systems%2C+)
26. Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. 2022. Pointnext: Revisiting pointnet++ with improved training and scaling strategies. Advances in neural information processing systems, 35:23192–23204. [find](https://scholar.google.com/scholar?q=Guocheng+Qian%2C+Yuchen+Li%2C+Houwen+Peng%2C+Jinjie+Mai%2C+Hasan+Hammoud%2C+Mohamed+Elhoseiny%2C+and+Bernard+Ghanem%2E+2022%2E+Pointnext%3A+Revisiting+pointnet%2B%2B+with+improved+training+and+scaling+strategies%2E+Advances+)
27. Linlu Qiu, Liwei Jiang, Ximing Lu, Melanie Sclar, Valentina Pyatkin, Chandra Bhagavatula, Bailin Wang, Yoon Kim, Yejin Choi, Nouha Dziri, et al. 2023. Phenomenal yet puzzling: Testing inductive reasoning capabilities of language models with hypothesis refinement. arXiv preprint arXiv:2310.08559. [find](https://scholar.google.com/scholar?q=Linlu+Qiu%2C+Liwei+Jiang%2C+Ximing+Lu%2C+Melanie+Sclar%2C+Valentina+Pyatkin%2C+Chandra+Bhagavatula%2C+Bailin+Wang%2C+Yoon+Kim%2C+Yejin+Choi%2C+Nouha+Dziri%2C+et+al%2E+2023%2E+Phenomenal+yet+puzzling%3A+Testing+inductive+reason)
28. Justus Randolph. 2019. A guide to writing the dissertation literature review. Practical assessment, research, and evaluation, 14(1):13. [find](https://scholar.google.com/scholar?q=Justus+Randolph%2E+2019%2E+A+guide+to+writing+the+dissertation+literature+review%2E+Practical+assessment%2C+research%2C+and+evaluation%2C+14%281%29%3A13%2E)
29. Nils Reimers and Iryna Gurevych. 2020. [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://md.research.elamur.ai/free/en/papers/reimers-2020-making-monolingual-sentence-embeddings-multilingual/). In EMNLP.
30. Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, and Emad Barsoum. 2025. [Agent laboratory: Using llm agents as research assistants](https://md.research.elamur.ai/free/en/papers/schmidgall-2025-agent-laboratory-using-llm/). arXiv preprint arXiv:2501.04227.
31. Chenglei Si, Diyi Yang, and Tatsunori Hashimoto. 2024. [Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers](https://md.research.elamur.ai/free/en/papers/si-2024-llms-generate-novel-research/). arXiv preprint arXiv:2409.04109.
32. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. 2013. [Recursive deep models for semantic compositionality over a sentiment treebank](https://md.research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/). In Proceedings of the 2013 conference on empirical methods in natural language processing, pages 1631…
33. 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)
34. Copilot Team. 2023a. copilot. URL: [https://github.com/features/copilot](https://github.com/features/copilot). [↗](https://github.com/features/copilot)
35. Ollama Team. 2023b. ollama. URL: [https://ollama.com/](https://ollama.com/). [↗](https://ollama.com/)
36. Changshuo Wang, Meiqing Wu, Siew-Kei Lam, Xin Ning, Shangshu Yu, Ruiping Wang, Weijun Li, and Thambipillai Srikanthan. 2024a. Gpsformer: A global perception and local structure fitting-based transformer for point cloud understanding. In European Conference on Computer Vision. Springer. [find](https://scholar.google.com/scholar?q=Changshuo+Wang%2C+Meiqing+Wu%2C+Siew%2DKei+Lam%2C+Xin+Ning%2C+Shangshu+Yu%2C+Ruiping+Wang%2C+Weijun+Li%2C+and+Thambipillai+Srikanthan%2E+2024a%2E+Gpsformer%3A+A+global+perception+and+local+structure+fitting%2Dbased+transform)
37. Peng-Shuai Wang. 2023. Octformer: Octree-based transformers for 3d point clouds. ACM Transactions on Graphics (TOG), 42(4):1–11. [find](https://scholar.google.com/scholar?q=Peng%2DShuai+Wang%2E+2023%2E+Octformer%3A+Octree%2Dbased+transformers+for+3d+point+clouds%2E+ACM+Transactions+on+Graphics+%28TOG%29%2C+42%284%29%3A1%E2%80%9311%2E)
38. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2023. [Scimon: Scientific inspiration machines optimized for novelty](https://md.research.elamur.ai/free/en/papers/wang-2023-scimon-scientific-inspiration-machines/). arXiv preprint arXiv:2305.14259.
39. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2024b. [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://md.research.elamur.ai/free/en/papers/wang-2023-scimon-scientific-inspiration-machines/). In ACL.
40. 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](https://md.research.elamur.ai/free/en/papers/wang-2024-autosurvey-large-language-models-automatically/). arXiv preprint arXiv:2406.10252.
41. Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. 2019. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog), 38(5):1–12. [find](https://scholar.google.com/scholar?q=Yue+Wang%2C+Yongbin+Sun%2C+Ziwei+Liu%2C+Sanjay+E+Sarma%2C+Michael+M+Bronstein%2C+and+Justin+M+Solomon%2E+2019%2E+Dynamic+graph+cnn+for+learning+on+point+clouds%2E+ACM+Transactions+on+Graphics+%28tog%29%2C+38%285%29%3A1%E2%80%9312%2E)
42. Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1912–1920. [find](https://scholar.google.com/scholar?q=Zhirong+Wu%2C+Shuran+Song%2C+Aditya+Khosla%2C+Fisher+Yu%2C+Linguang+Zhang%2C+Xiaoou+Tang%2C+and+Jianxiong+Xiao%2E+2015%2E+3d+shapenets%3A+A+deep+representation+for+volumetric+shapes%2E+In+Proceedings+of+the+IEEE+conferen)
43. Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, Bin Wang, Bo Zhang, and Lei Bai. 2025. [Surveyforge: On the outline heuristics, memory-driven generation, and multi-dimensional evaluation for automated survey writing](https://md.research.elamur.ai/free/en/papers/yan-2025-surveyforge-outline-heuristics-memory-driven/). arXiv preprint arXiv:2503.04629.
44. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. 2024a. Qwen2 technical report. arXiv preprint arXiv:2407.10671. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+et+al%2E+2024a%2E+Qwen2+technical+report%2E+arXiv+preprint+arXiv%3A2407%2E10671%2E)
45. Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, and E. Cambria. 2024b. [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-automated/). ACL Findings.
46. Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, and Erik Cambria. 2023. [Large language models for automated open-domain scientific hypotheses discovery](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-automated/). arXiv preprint arXiv:2309.02726.
47. Shunyu Yao, Qingqing Ke, Qiwei Wang, Kangtong Li, and Jie Hu. 2024. Lawyer gpt: A legal large language model with enhanced domain knowledge and reasoning capabilities. In Proceedings of the 2024 3rd International Symposium on Robotics, Artificial Intelligence and Information Engineering, RAIIE ’24,… [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Qingqing+Ke%2C+Qiwei+Wang%2C+Kangtong+Li%2C+and+Jie+Hu%2E+2024%2E+Lawyer+gpt%3A+A+legal+large+language+model+with+enhanced+domain+knowledge+and+reasoning+capabilities%2E+In+Proceedings+of+the+2024+3rd+I)
48. Sergey Zagoruyko. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146. — [arXiv:1605.07146](https://arxiv.org/abs/1605.07146) [find](https://scholar.google.com/scholar?q=Sergey+Zagoruyko%2E+2016%2E+Wide+residual+networks%2E+arXiv+preprint+arXiv%3A1605%2E07146%2E+%E2%80%94+%5BarXiv%3A1605%2E07146%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1605%2E07146%29)
49. Lei Zhang, Yuge Zhang, Kan Ren, Dongsheng Li, and Yuqing Yang. 2023a. [Mlcopilot: Unleashing the power of large language models in solving machine learning tasks](https://md.research.elamur.ai/free/en/papers/zhang-2024-mlcopilot-unleashing-power-large-language/). arXiv preprint arXiv:2304.14979.
50. Shujian Zhang, Chengyue Gong, Lemeng Wu, Xingchao Liu, and Mingyuan Zhou. 2023b. [Automl-gpt: Automatic machine learning with gpt](https://md.research.elamur.ai/free/en/papers/zhang-2023-automl-gpt-automatic-machine-learning/). arXiv preprint arXiv:2305.02499.
51. Yangqiaoyu Zhou, Haokun Liu, Tejes Srivastava, Hongyuan Mei, and Chenhao Tan. 2024. [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.
52. Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y Wu, Yukun Li, Huazuo Gao, Shirong Ma, et al. 2024. [Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2024-deepseek-coder-v2-breaking-barrier/). arXiv preprint arXiv:2406.11931.
53. Outlines for Appendix In Appendix, we provide additional details and qualitative results on the following aspects: • Appendix A: Further details of D OLPHIN including prompts, qualitative results for each step, and so on: – Appendix A.1: Ideas generation process. – Appendix A.2: Experimental verific… [find](https://scholar.google.com/scholar?q=Outlines+for+Appendix+In+Appendix%2C+we+provide+additional+details+and+qualitative+results+on+the+following+aspects%3A+%E2%80%A2+Appendix+A%3A+Further+details+of+D+OLPHIN+including+prompts%2C+qualitative+results+for+)

*Updated 3 November 2026*