---
title: "InternAgent — paper by Team et al. (2025) — summary and ideas"
description: "Automating science with LLM agents faces two obstacles. 51 references, cited by 20 papers here."
authors: ["InternAgent Team", "Bo Zhang", "Shiyang Feng", "Xiangchao Yan", "Jiakang Yuan", "Runmin Ma", "Yusong Hu", "Zhiyin Yu", "Xiaohan He", "Songtao Huang", "Shaowei Hou", "Zheng Nie", "Zhilong Wang", "Jinyao Liu", "Tianshuo Peng", "Peng Ye", "Dongzhan Zhou", "Shufei Zhang", "Xiaosong Wang", "Yilan Zhang", "Meng Li", "Zhongying Tu", "Xiangyu Yue", "Wangli Ouyang", "Bowen Zhou", "Lei Bai"]
year: 2025
venue: "arXiv:2505.16938"
source: "https://arxiv.org/abs/2505.16938"
doi: "10.48550/arxiv.2505.16938"
arxiv: "2505.16938"
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/team-2025-internagent-agent-becomes-scientist/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/team-2025-internagent-agent-becomes-scientist/)

[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/) / InternAgent: When Agent Becomes the Scientist — Building Closed-Loop System from Hypothesis to Verification

# InternAgent: When Agent Becomes the Scientist — Building Closed-Loop System from Hypothesis to Verification

**Authors:** InternAgent Team, [Bo Zhang](https://md.research.elamur.ai/free/en/authors/bo-zhang/), [Shiyang Feng](https://md.research.elamur.ai/free/en/authors/shiyang-feng/), [Xiangchao Yan](https://md.research.elamur.ai/free/en/authors/xiangchao-yan/), [Jiakang Yuan](https://md.research.elamur.ai/free/en/authors/jiakang-yuan/), Runmin Ma, Yusong Hu, [Zhiyin Yu](https://md.research.elamur.ai/free/en/authors/zhiyin-yu/), Xiaohan He, Songtao Huang, Shaowei Hou, Zheng Nie, Zhilong Wang, Jinyao Liu, Tianshuo Peng, [Peng Ye](https://md.research.elamur.ai/free/en/authors/peng-ye/), [Dongzhan Zhou](https://md.research.elamur.ai/free/en/authors/dongzhan-zhou/), [Shufei Zhang](https://md.research.elamur.ai/free/en/authors/shufei-zhang/), Xiaosong Wang, Yilan Zhang, Meng Li, Zhongying Tu, [Xiangyu Yue](https://md.research.elamur.ai/free/en/authors/xiangyu-yue/), Wangli Ouyang, [Bowen Zhou](https://md.research.elamur.ai/free/en/authors/bowen-zhou/) and [Lei Bai](https://md.research.elamur.ai/free/en/authors/lei-bai/) · **Year:** 2025 · **Venue:** arXiv:2505.16938 · **Licence:** [arXiv non-exclusive distribution license](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2505.16938) · [PDF](https://arxiv.org/pdf/2505.16938) · [DOI 10.48550/arxiv.2505.16938](https://doi.org/10.48550/arxiv.2505.16938) · [arXiv 2505.16938](https://arxiv.org/abs/2505.16938) · [OpenAlex](https://openalex.org/W4417439318)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [20](https://md.research.elamur.ai/free/en/papers/team-2025-internagent-agent-becomes-scientist/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Automating science with LLM agents faces two obstacles. Systems must produce hypotheses that are both new and sound, and they must close the loop by implementing and testing them. The InternAgent Team at Shanghai Artificial Intelligence Laboratory tackles both with InternAgent, a multi-agent framework that carries a research task from an initial idea to experimental verification.

The pipeline has three stages. First, literature-grounded ideas evolve through critique, ranking and optional input from human experts. Second, rough proposals become detailed, implementable methods. Third, multi-round experiment planning lets coding agents modify baseline code, debug it and feed results back.

The authors tested the system on 12 tasks from AI and the natural sciences. AI tasks included image and 3D classification, segmentation, sentiment classification and MLLM fine-tuning. Science tasks included reaction yield, molecular dynamics and enhancer activity. InternAgent improved baselines within hours, whereas the authors say human researchers usually need months for similar gains.

The work matters because it moves autonomous research beyond idea generation toward empirically verified improvements across many domains. Baselines and generated code are publicly released.

## Key points
- **Agents and coding tools.** InternAgent coordinates specialized agents: Survey Agent, Idea Innovation Agent, Assessment Agent, Method Development Agent, Orchestration Agent, Code Review Agent and Coding Agent. Coding builds on tools such as Openhands and Aider.
- **Survey Agent modes.** It offers a broad "literature review" mode, which searches with keyword combinations and screens abstracts for relevance. It also has a more thorough "deep research" mode.
- **Reaction yield prediction.** The abstract reports a rise from 27.6% to 35.4% in about 12 hours. The introduction gives slightly different figures for the same task: 24.2% ± 4.2 rising to 34.8% ± 1.1.
- **Other reported gains.**
  - Enhancer activity prediction: Pearson correlation rose from 0.65 (DeepSTARR baseline) to 0.79 in roughly 4 hours.
  - 2D semantic segmentation: precision rose from 78.8% to 81.0% in about 30 hours.
- **Open resources.** Code, baselines and generated solutions are on GitHub (Alpha-Innovator/InternAgent), with a model release at huggingface.co/U4R/InternAgent. Planned future work covers:
  - better knowledge retrieval
  - knowledge understanding and representation
  - stronger agent self-improvement
  - benchmarks that judge an idea's real value, not only its novelty

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

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 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: InternAgent Team, Bo Zhang, Shiyang Feng, Xiangchao Yan, Jiakang Yuan, Runmin Ma, Yusong Hu, Zhiyin Yu, Xiaohan He, Songtao Huang, Shaowei Hou, Zheng Nie, Zhilong Wang, Jinyao Liu, Tianshuo Peng, Peng Ye, Dongzhan Zhou, Shufei Zhang, Xiaosong Wang, Yilan Zhang, Meng Li, Zhongying Tu, Xiangyu Yue, Wangli Ouyang, Bowen Zhou and Lei Bai. 2025. InternAgent: When Agent Becomes the Scientist — Building Closed-Loop System from Hypothesis to Verification. arXiv:2505.16938.

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

```bibtex
@misc{team2025internagent,
  title = {{InternAgent: When Agent Becomes the Scientist — Building Closed-Loop System from Hypothesis to Verification}},
  author = {InternAgent Team, Bo Zhang, Shiyang Feng, Xiangchao Yan, Jiakang Yuan, Runmin Ma, Yusong Hu, Zhiyin Yu, Xiaohan He, Songtao Huang, Shaowei Hou, Zheng Nie, Zhilong Wang, Jinyao Liu, Tianshuo Peng, Peng Ye, Dongzhan Zhou, Shufei Zhang, Xiaosong Wang, Yilan Zhang, Meng Li, Zhongying Tu, Xiangyu Yue, Wangli Ouyang, Bowen Zhou and Lei Bai},
  year = {2025},
  doi = {10.48550/arxiv.2505.16938},
  eprint = {2505.16938},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2505.16938}
}
```

- [← previous Intention Analysis Makes LLMs A Good Jailbreak Defender](https://md.research.elamur.ai/free/en/papers/zhang-2025-intention-analysis-makes-llms-good/)
- [next → KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding](https://md.research.elamur.ai/free/en/papers/heakl-2025-kitab-bench-comprehensive-multi-domain/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

51 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Cosmas D Arnold, Daniel Gerlach, Christoph Stelzer, Łukasz M Boryń, Martina Rath, and Alexander Stark. Genome-wide quantitative enhancer activity maps identified by starr-seq. Science, 339(6123):1074–1077, 2013. [find](https://scholar.google.com/scholar?q=Cosmas+D+Arnold%2C+Daniel+Gerlach%2C+Christoph+Stelzer%2C+%C5%81ukasz+M+Boryn%CC%81%2C+Martina+Rath%2C+and+Alexander+Stark%2E+Genome%2Dwide+quantitative+enhancer+activity+maps+identified+by+starr%2Dseq%2E+Science%2C+339%286123%29%3A1074)
2. Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), pp. 801–818, 2018. [find](https://scholar.google.com/scholar?q=Liang%2DChieh+Chen%2C+Yukun+Zhu%2C+George+Papandreou%2C+Florian+Schroff%2C+and+Hartwig+Adam%2E+Encoder%2Ddecoder+with+atrous+separable+convolution+for+semantic+image+segmentation%2E+In+Proceedings+of+the+European+con)
3. Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, et al. [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/). Science China Information Sciences, 67(12):220101, 2024.
4. Stefan Chmiela, Alexandre Tkatchenko, Huziel E Sauceda, Igor Poltavsky, Kristof T Schütt, and Klaus-Robert Müller. Machine learning of accurate energy-conserving molecular force fields. Science advances, 3(5):e1603015, 2017. [find](https://scholar.google.com/scholar?q=Stefan+Chmiela%2C+Alexandre+Tkatchenko%2C+Huziel+E+Sauceda%2C+Igor+Poltavsky%2C+Kristof+T+Sch%C3%BCtt%2C+and+Klaus%2DRobert+M%C3%BCller%2E+Machine+learning+of+accurate+energy%2Dconserving+molecular+force+fields%2E+Science+advanc)
5. Bernardo P de Almeida, Franziska Reiter, Michaela Pagani, and Alexander Stark. Deepstarr predicts enhancer activity from dna sequence and enables the de novo design of synthetic enhancers. Nature genetics, 54(5):613–624, 2022. [find](https://scholar.google.com/scholar?q=Bernardo+P+de+Almeida%2C+Franziska+Reiter%2C+Michaela+Pagani%2C+and+Alexander+Stark%2E+Deepstarr+predicts+enhancer+activity+from+dna+sequence+and+enables+the+de+novo+design+of+synthetic+enhancers%2E+Nature+gene)
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. [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, pp. 4171–4186, 2019.
7. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PAS-CAL Visual Object Classes Challenge 2012 (VOC2012) Results. [http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html](http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html), 2012. [↗](http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html)
8. Paul Gauthier and Aider-AI Contributors. Aider: Ai pair programming in your terminal. [https://github.com/Aider-AI/aider](https://github.com/Aider-AI/aider), 2023. URL https://github.com/Aider-AI/aider. Accessed: 2025-05-07. [↗](https://github.com/Aider-AI/aider)
9. 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/).
10. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948, 2025.
11. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276, 2024.
12. Alex Krizhevsky, Geoffrey Hinton, et al. Learning multiple layers of features from tiny images. 2009. [find](https://scholar.google.com/scholar?q=Alex+Krizhevsky%2C+Geoffrey+Hinton%2C+et+al%2E+Learning+multiple+layers+of+features+from+tiny+images%2E+2009%2E)
13. HKU Data Intelligence Lab. Ai-researcher: Fully-automated scientific discovery with llm agents. [https://github.com/HKUDS/AI-Researcher](https://github.com/HKUDS/AI-Researcher), 2025. URL https://github.com/HKUDS/AI-Researcher. [↗](https://github.com/HKUDS/AI-Researcher)
14. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, et al. [Llava-onevision: Easy visual task transfer](https://md.research.elamur.ai/free/en/papers/li-2024-llava-onevision-easy-visual-task/). arXiv preprint arXiv:2408.03326, 2024a.
15. Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xinxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, et al. Chain of ideas: Revolutionizing research in novel idea development with llm agents. arXiv preprint arXiv:2410.[13185, 2024b](https://md.research.elamur.ai/free/en/papers/li-2024-chain-ideas-revolutionizing-research/).
16. 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.
17. Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. [Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts](https://md.research.elamur.ai/free/en/papers/lu-2023-mathvista-evaluating-mathematical-reasoning-foundation/). arXiv preprint arXiv:2310.02255, 2023.
18. Ruilin Luo, Zhuofan Zheng, Yifan Wang, Yiyao Yu, Xinzhe Ni, Zicheng Lin, Jin Zeng, and Yujiu Yang. Ursa: Understanding and verifying chain-of-thought reasoning in multimodal mathematics. arXiv preprint arXiv:2501.04686, 2025. — [arXiv:2501.04686](https://arxiv.org/abs/2501.04686) [find](https://scholar.google.com/scholar?q=Ruilin+Luo%2C+Zhuofan+Zheng%2C+Yifan+Wang%2C+Yiyao+Yu%2C+Xinzhe+Ni%2C+Zicheng+Lin%2C+Jin+Zeng%2C+and+Yujiu+Yang%2E+Ursa%3A+Understanding+and+verifying+chain%2Dof%2Dthought+reasoning+in+multimodal+mathematics%2E+arXiv+preprin)
19. Jiageng Mao, Minzhe Niu, Chenhan Jiang, Hanxue Liang, Jingheng Chen, Xiaodan Liang, Yamin Li, Chaoqiang Ye, Wei Zhang, Zhenguo Li, et al. One million scenes for autonomous driving: Once dataset. arXiv preprint arXiv:2106.11037, 2021. — [arXiv:2106.11037](https://arxiv.org/abs/2106.11037) [find](https://scholar.google.com/scholar?q=Jiageng+Mao%2C+Minzhe+Niu%2C+Chenhan+Jiang%2C+Hanxue+Liang%2C+Jingheng+Chen%2C+Xiaodan+Liang%2C+Yamin+Li%2C+Chaoqiang+Ye%2C+Wei+Zhang%2C+Zhenguo+Li%2C+et+al%2E+One+million+scenes+for+autonomous+driving%3A+Once+dataset%2E+arXiv)
20. Thomas M Norman, Max A Horlbeck, Joseph M Replogle, Alex Y Ge, Albert Xu, Marco Jost, Luke A Gilbert, and Jonathan S Weissman. Exploring genetic interaction manifolds constructed from rich single-cell phenotypes. Science, 365(6455):786–793, 2019. [find](https://scholar.google.com/scholar?q=Thomas+M+Norman%2C+Max+A+Horlbeck%2C+Joseph+M+Replogle%2C+Alex+Y+Ge%2C+Albert+Xu%2C+Marco+Jost%2C+Luke+A+Gilbert%2C+and+Jonathan+S+Weissman%2E+Exploring+genetic+interaction+manifolds+constructed+from+rich+single%2Dcell)
21. Damith Perera, Joseph W Tucker, Shalini Brahmbhatt, Christopher J Helal, Ashley Chong, William Farrell, Paul Richardson, and Neal W Sach. A platform for automated nanomole-scale reaction screening and micromole-scale synthesis in flow. Science, 359(6374):429–434, 2018. [find](https://scholar.google.com/scholar?q=Damith+Perera%2C+Joseph+W+Tucker%2C+Shalini+Brahmbhatt%2C+Christopher+J+Helal%2C+Ashley+Chong%2C+William+Farrell%2C+Paul+Richardson%2C+and+Neal+W+Sach%2E+A+platform+for+automated+nanomole%2Dscale+reaction+screening+and)
22. Biqing Qi, Kaiyan Zhang, Haoxiang Li, Kai Tian, Sihang Zeng, Zhang-Ren Chen, and Bowen Zhou. [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, 2023.
23. Biqing Qi, Kaiyan Zhang, Kai Tian, Haoxiang Li, Zhang-Ren Chen, Sihang Zeng, Ermo Hua, Hu Jinfang, and Bowen Zhou. [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, 2024.
24. Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 652–660, 2017. [find](https://scholar.google.com/scholar?q=Charles+R+Qi%2C+Hao+Su%2C+Kaichun+Mo%2C+and+Leonidas+J+Guibas%2E+Pointnet%3A+Deep+learning+on+point+sets+for+3d+classification+and+segmentation%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+patt)
25. Yansheng Qiu, Haoquan Zhang, Zhaopan Xu, Ming Li, Diping Song, Zheng Wang, and Kaipeng Zhang. Ai idea bench 2025: Ai research idea generation benchmark. arXiv preprint arXiv:2504.14191, 2025. — [arXiv:2504.14191](https://arxiv.org/abs/2504.14191) [find](https://scholar.google.com/scholar?q=Yansheng+Qiu%2C+Haoquan+Zhang%2C+Zhaopan+Xu%2C+Ming+Li%2C+Diping+Song%2C+Zheng+Wang%2C+and+Kaipeng+Zhang%2E+Ai+idea+bench+2025%3A+Ai+research+idea+generation+benchmark%2E+arXiv+preprint+arXiv%3A2504%2E14191%2C+2025%2E+%E2%80%94+%5BarXiv)
26. Yusuf Roohani, Kexin Huang, and Jure Leskovec. Predicting transcriptional outcomes of novel multigene perturbations with gears. Nature Biotechnology, 42(6):927–935, 2024. [find](https://scholar.google.com/scholar?q=Yusuf+Roohani%2C+Kexin+Huang%2C+and+Jure+Leskovec%2E+Predicting+transcriptional+outcomes+of+novel+multigene+perturbations+with+gears%2E+Nature+Biotechnology%2C+42%286%29%3A927%E2%80%93935%2C+2024%2E)
27. Samuel Schmidgall and Michael Moor. [Agentrxiv: Towards collaborative autonomous research](https://md.research.elamur.ai/free/en/papers/schmidgall-2025-agentrxiv-collaborative-autonomous-research/). arXiv preprint arXiv:2503.18102, 2025.
28. Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, and Emad Barsoum. [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, 2025.
29. Chenglei Si, Diyi Yang, and Tatsunori Hashimoto. [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, 2024.
30. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. [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, pp. 1631–1642, 2…
31. OpenPCDet Development Team. Openpcdet: An open-source toolbox for 3d object detection from point clouds. [https://github.com/open-mmlab/OpenPCDet](https://github.com/open-mmlab/OpenPCDet), 2020. [↗](https://github.com/open-mmlab/OpenPCDet)
32. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, et al. Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution. arXiv preprint arXiv:2409.[12191, 2024a](https://md.research.elamur.ai/free/en/papers/wang-2024-qwen2-vl-enhancing-vision/).
33. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. [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, 2023.
34. Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, a… — [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://md.research.elamur.ai/free/en/papers/wang-2024-openhands-open-platform-ai/)
35. Xingyao Wang, Boxuan Li, Yufan Song, Frank F Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, et al. [Openhands: An open platform for ai software developers as generalist agents](https://md.research.elamur.ai/free/en/papers/wang-2024-openhands-open-platform-ai/). In The Thirteenth International Conference on Learning Representations, 2024c.
36. Yusong Wang, Tong Wang, Shaoning Li, Xinheng He, Mingyu Li, Zun Wang, Nanning Zheng, Bin Shao, and Tie-Yan Liu. Enhancing geometric representations for molecules with equivariant vector-scalar interactive message passing. Nature Communications, 15(1): 313, 2024d. [find](https://scholar.google.com/scholar?q=Yusong+Wang%2C+Tong+Wang%2C+Shaoning+Li%2C+Xinheng+He%2C+Mingyu+Li%2C+Zun+Wang%2C+Nanning+Zheng%2C+Bin+Shao%2C+and+Tie%2DYan+Liu%2E+Enhancing+geometric+representations+for+molecules+with+equivariant+vector%2Dscalar+interac)
37. Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1912–1920, 2015. [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+3d+shapenets%3A+A+deep+representation+for+volumetric+shapes%2E+In+Proceedings+of+the+IEEE+conference+on+)
38. 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.
39. Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, Bin Wang, Bo Zhang, and Lei Bai. Surveyforge: On the outline heuristics, memory-driven generation, and multi-dimensional evaluation for automated survey writing. arXiv preprint arXiv:2503.[04629, 2025](https://md.research.elamur.ai/free/en/papers/yan-2025-surveyforge-outline-heuristics-memory-driven/).
40. An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, et al. Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement, 2024b. [URL https://arxiv.org/abs/2409.12122](https://md.research.elamur.ai/free/en/papers/yang-2024-qwen2-5-math-technical-report/). [↗](https://arxiv.org/abs/2409.12122)
41. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115, 2024. [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+Qwen2%2E+5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115%2C+2024%2E)
42. Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, and Erik Cambria. [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, 2023.
43. Tianwei Yin, Xingyi Zhou, and Philipp Krahenbuhl. Center-based 3d object detection and tracking. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 11784–11793, 2021. [find](https://scholar.google.com/scholar?q=Tianwei+Yin%2C+Xingyi+Zhou%2C+and+Philipp+Krahenbuhl%2E+Center%2Dbased+3d+object+detection+and+tracking%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+recognition%2C+pp%2E+11784%E2%80%9311793%2C+)
44. Jiakang Yuan, Xiangchao Yan, Botian Shi, Tao Chen, Wanli Ouyang, Bo Zhang, Lei Bai, Yu Qiao, and Bowen Zhou. Dolphin: Closed-loop open-ended auto-research through thinking, practice, and feedback. arXiv preprint arXiv:2501.[03916, 2025](https://md.research.elamur.ai/free/en/papers/yuan-2025-dolphin-moving-closed-loop/).
45. Sergey Zagoruyko. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016. — [arXiv:1605.07146](https://arxiv.org/abs/1605.07146) [find](https://scholar.google.com/scholar?q=Sergey+Zagoruyko%2E+Wide+residual+networks%2E+arXiv+preprint+arXiv%3A1605%2E07146%2C+2016%2E+%E2%80%94+%5BarXiv%3A1605%2E07146%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1605%2E07146%29)
46. Ailing Zeng, Muxi Chen, Lei Zhang, and Qiang Xu. Are transformers effective for time series forecasting? In Proceedings of the AAAI conference on artificial intelligence, volume 37, pp. 11121–11128, 2023. [find](https://scholar.google.com/scholar?q=Ailing+Zeng%2C+Muxi+Chen%2C+Lei+Zhang%2C+and+Qiang+Xu%2E+Are+transformers+effective+for+time+series+forecasting%3F+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligence%2C+volume+37%2C+pp%2E+11121%E2%80%9311128%2C+2)
47. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. [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, pp. 11975–11986, 2023.
48. Zhen Zhao, Zhen Huang, Zicheng Wang, Wenqi Huang, and LEI BAI. Senseflow: A physics-informed and self-ensembling iterative framework for power flow estimation, 2024. URL [https://openreview.net/forum?id=UKiCFpwcqY](https://openreview.net/forum?id=UKiCFpwcqY). [↗](https://openreview.net/forum?id=UKiCFpwcqY)
49. Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, and Wancai Zhang. Informer: Beyond efficient transformer for long sequence time-series forecasting. In The Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Virtual Conference, volume 35, pp. 11106–11115. [find](https://scholar.google.com/scholar?q=Haoyi+Zhou%2C+Shanghang+Zhang%2C+Jieqi+Peng%2C+Shuai+Zhang%2C+Jianxin+Li%2C+Hui+Xiong%2C+and+Wancai+Zhang%2E+Informer%3A+Beyond+efficient+transformer+for+long+sequence+time%2Dseries+forecasting%2E+In+The+Thirty%2DFifth+AAA)
50. 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.
51. Ray Daniel Zimmerman, Carlos Edmundo Murillo-Sánchez, and Robert John Thomas. Matpower: Steady-state operations, planning, and analysis tools for power systems research and education. IEEE Transactions on power systems, 26(1):12–19, 2010. [find](https://scholar.google.com/scholar?q=Ray+Daniel+Zimmerman%2C+Carlos+Edmundo+Murillo%2DS%C3%A1nchez%2C+and+Robert+John+Thomas%2E+Matpower%3A+Steady%2Dstate+operations%2C+planning%2C+and+analysis+tools+for+power+systems+research+and+education%2E+IEEE+Transaction)

*Updated 3 November 2026*