---
title: "AI-Researcher: Autonomous Scientific Innovation (2025)"
description: "The authors, from The University of Hong Kong, present AI-Researcher, an agent-based framework… 27 references, cited by 35 papers here."
authors: ["Jiabin Tang", "Lianghao Xia", "Zhonghang Li", "Chao Huang"]
year: 2025
venue: "arXiv:2505.18705"
source: "https://arxiv.org/abs/2505.18705"
doi: "10.48550/arxiv.2505.18705"
arxiv: "2505.18705"
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/tang-2025-ai-researcher-autonomous-scientific/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tang-2025-ai-researcher-autonomous-scientific/)

[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/3/) / AI-Researcher: Autonomous Scientific Innovation

# AI-Researcher: Autonomous Scientific Innovation

**Authors:** [Jiabin Tang](https://md.research.elamur.ai/free/en/authors/jiabin-tang/), [Lianghao Xia](https://md.research.elamur.ai/free/en/authors/lianghao-xia/), [Zhonghang Li](https://md.research.elamur.ai/free/en/authors/zhonghang-li/) and [Chao Huang](https://md.research.elamur.ai/free/en/authors/chao-huang/) · **Year:** 2025 · **Venue:** [arXiv:2505.18705](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/) ([NeurIPS 2025](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/)) · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2505.18705) · [PDF](https://arxiv.org/pdf/2505.18705) · [DOI 10.48550/arxiv.2505.18705](https://doi.org/10.48550/arxiv.2505.18705) · [arXiv 2505.18705](https://arxiv.org/abs/2505.18705) · [OpenAlex](https://openalex.org/W4414581606)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [35](https://md.research.elamur.ai/free/en/papers/tang-2025-ai-researcher-autonomous-scientific/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Large language models now handle coding and mathematical reasoning well, but turning these skills into a system that does original research on its own is still unsolved. Real discovery means searching huge solution spaces with uncertain payoff, making sense of large bodies of literature, and dropping unpromising ideas. The authors, from The University of Hong Kong, present AI-Researcher, an agent-based framework designed to run the whole research cycle with little human involvement. It surveys prior work, proposes hypotheses, implements and tests algorithms, and drafts a manuscript ready for submission. To evaluate systems of this kind, they also build Scientist-Bench, a benchmark based on recent state-of-the-art papers from several AI subfields. It has two task types: guided innovation, where a research direction is supplied, and open-ended exploration. The authors report that the system implements its ideas successfully at high rates and writes papers whose quality nears that of human researchers. The work offers both a framework and a testbed for treating AI as an independent research contributor rather than a narrow assistant.

## Key points
- **System:** AI-Researcher is an end-to-end autonomous pipeline covering literature review, hypothesis generation, algorithm implementation and manuscript writing. Code is at github.com/HKUDS/AI-Researcher.
- **Benchmark:** Scientist-Bench is built from state-of-the-art papers across diverse AI research domains. It combines guided-innovation tasks with open-ended exploration tasks.
- **Reported results:** The authors claim high implementation success rates and generated papers approaching human-level quality. No specific figures appear in the provided excerpt (abstract and introduction only).
- **Authors and publication:** Jiabin Tang and Lianghao Xia (equal contribution), Zhonghang Li, and Chao Huang (corresponding author), The University of Hong Kong. Preprint arXiv:2505.18705, May 2025, under review.

*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

- [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/) — University, Pok Fu Lam, China · 127 works · 13,824 citations
- [University of Rochester](https://md.research.elamur.ai/free/en/universities/university-of-rochester/) — University, Rochester, United States · 46 works · 7,948 citations

📚 Shelves (4): [🖥️ 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

## Cite

Cite as: Jiabin Tang, Lianghao Xia, Zhonghang Li and Chao Huang. 2025. AI-Researcher: Autonomous Scientific Innovation. arXiv:2505.18705.

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

```bibtex
@misc{tang2025ai,
  title = {{AI-Researcher: Autonomous Scientific Innovation}},
  author = {Jiabin Tang, Lianghao Xia, Zhonghang Li and Chao Huang},
  year = {2025},
  doi = {10.48550/arxiv.2505.18705},
  eprint = {2505.18705},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2505.18705}
}
```

- [← previous A Systematic Survey of Automatic Prompt Optimization Techniques](https://md.research.elamur.ai/free/en/papers/ramnath-2025-systematic-survey-automatic-prompt-optimization/)
- [next → DeepRAG: Thinking to Retrieve Step by Step for Large Language Models](https://md.research.elamur.ai/free/en/papers/guan-2025-deeprag-thinking-retrieve-step-step/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

27 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Hanchen Wang, Tianfan Fu, Yuanqi Du, Wenhao Gao, Kexin Huang, Ziming Liu, Payal Chandak, Shengchao Liu, Peter Van Katwyk, Andreea Deac, et al. Scientific discovery in the age of artificial intelligence. Nature, 620(7972):47–60, 2023. [find](https://scholar.google.com/scholar?q=Hanchen+Wang%2C+Tianfan+Fu%2C+Yuanqi+Du%2C+Wenhao+Gao%2C+Kexin+Huang%2C+Ziming+Liu%2C+Payal+Chandak%2C+Shengchao+Liu%2C+Peter+Van+Katwyk%2C+Andreea+Deac%2C+et+al%2E+Scientific+discovery+in+the+age+of+artificial+intelligenc)
2. Aniket Didolkar, Anirudh Goyal, Nan Rosemary Ke, Siyuan Guo, Michal Valko, Timothy Lillicrap, Danilo Jimenez Rezende, Yoshua Bengio, Michael C Mozer, and Sanjeev Arora. [Metacognitive capabilities of llms: An exploration in mathematical problem solving](https://md.research.elamur.ai/free/en/papers/didolkar-2024-metacognitive-capabilities-llms-exploration-mathematical/). NeurIPS, 37:19783–19812, 2024.
3. Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Yu Wu, YK Li, et al. Deepseek-coder: When the large language model meets programming–the rise of code intelligence. arXiv preprint arXiv:2401.14196, 2024. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Qihao+Zhu%2C+Dejian+Yang%2C+Zhenda+Xie%2C+Kai+Dong%2C+Wentao+Zhang%2C+Guanting+Chen%2C+Xiao+Bi%2C+Yu+Wu%2C+YK+Li%2C+et+al%2E+Deepseek%2Dcoder%3A+When+the+large+language+model+meets+programming%E2%80%93the+rise+of+code+inte)
4. Manus Technologies. Manus: Structured and ai-assisted academic writing tool. [https://manus.im/](https://manus.im/), 2025. [↗](https://manus.im/)
5. OpenManus Contributors. Openmanus: Open-source framework for building general ai agents. [https://openmanus.github.io/](https://openmanus.github.io/), 2025. [↗](https://openmanus.github.io/)
6. Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. [Camel: Communicative agents for "mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/), 2023. URL https://arxiv.org/abs/2303.17760. [↗](https://arxiv.org/abs/2303.17760)
7. Jiabin Tang, Tianyu Fan, and Chao Huang. [Autoagent: A fully-automated and zero-code framework for llm agents](https://md.research.elamur.ai/free/en/papers/tang-2026-autoagent-fully-automated-zero-code/), 2025. URL https://arxiv.org/abs/2502.05957. [↗](https://arxiv.org/abs/2502.05957)
8. Samuel Schmidgall and Michael Moor. [Agentrxiv: Towards collaborative autonomous research](https://md.research.elamur.ai/free/en/papers/schmidgall-2025-agentrxiv-collaborative-autonomous-research/), 2025. URL https://arxiv.org/abs/2503.18102. [↗](https://arxiv.org/abs/2503.18102)
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. Chandan K Reddy and Parshin Shojaee. Towards scientific discovery with generative ai: Progress, opportunities, and challenges. Proceedings of the AAAI Conference on Artificial Intelligence, pages 28601–28609, 2025. [find](https://scholar.google.com/scholar?q=Chandan+K+Reddy+and+Parshin+Shojaee%2E+Towards+scientific+discovery+with+generative+ai%3A+Progress%2C+opportunities%2C+and+challenges%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+pages+2860)
11. Xiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu, Jieyu Zhang, Satyen Subramaniam, Arjun R. Loomba, Shichang Zhang, Yizhou Sun, and Wei Wang. [Scibench: Evaluating college-level scientific problem-solving abilities of large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-scibench-evaluating-college-level-scientific/), 2024. URL https://arxiv.org/abs/2307.10635. [↗](https://arxiv.org/abs/2307.10635)
12. 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/), 2024. URL https://arxiv.org/abs/2408.06292. [↗](https://arxiv.org/abs/2408.06292)
13. 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/), 2025. URL https://arxiv.org/abs/2504.08066. [↗](https://arxiv.org/abs/2504.08066)
14. Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, Deli Zhao, Yu Rong, Tian Feng, and Lidong Bing. [Chain of ideas: Revolutionizing research via novel idea development with llm agents](https://md.research.elamur.ai/free/en/papers/li-2024-chain-ideas-revolutionizing-research/), 2024. URL https://arxiv.org/abs/2410.1318… [↗](https://arxiv.org/abs/2410.1318…)
15. Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, and Sung Ju Hwang. [Researchagent: Iterative research idea generation over scientific literature with large language models](https://md.research.elamur.ai/free/en/papers/baek-2024-researchagent-iterative-research-idea/), 2025. URL https://arxiv.org/abs/2404.07738. [↗](https://arxiv.org/abs/2404.07738)
16. 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/). CoRR, abs/2409.04109, 2024.
17. Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, and Monica S. Lam. [Assisting in writing wikipedia-like articles from scratch with large language models](https://md.research.elamur.ai/free/en/papers/shao-2024-assisting-writing-wikipedia-like-articles/). In NAACL-HLT, pages 6252–6278. Association for Computational Linguistics, 2024.
18. Yiqiao Jin, Qinlin Zhao, Yiyang Wang, Hao Chen, Kaijie Zhu, Yijia Xiao, and Jindong Wang. [Agentreview: Exploring peer review dynamics with llm agents](https://md.research.elamur.ai/free/en/papers/jin-2024-agentreview-exploring-peer-review/). EMNLP, 2024.
19. LangChain Contributors. Langchain: Build context-aware reasoning applications. [https://github.com/langchain-ai/langchain](https://github.com/langchain-ai/langchain), 2023. [↗](https://github.com/langchain-ai/langchain)
20. Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. [Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face](https://md.research.elamur.ai/free/en/papers/shen-2023-hugginggpt-solving-ai-tasks-chatgpt/), 2023. URL https://arxiv.org/abs/2303.17580. [↗](https://arxiv.org/abs/2303.17580)
21. Tianbao Xie, Fan Zhou, Zhoujun Cheng, Peng Shi, Luoxuan Weng, Yitao Liu, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, and Tao Yu. [Openagents: An open platform for language agents in the wild](https://md.research.elamur.ai/free/en/papers/xie-2023-openagents-open-platform-language-agents/), 2023. URL https://arxiv.org/abs/2310.1063… [↗](https://arxiv.org/abs/2310.1063…)
22. Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. [Metagpt: Meta programming for a multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/), 2024. URL https:/…
23. Microsoft AutoGen Team. Autogen: A programming framework for agentic ai. [https://github.com/microsoft/autogen](https://github.com/microsoft/autogen), 2025. Accessed: 2025-04-21. [↗](https://github.com/microsoft/autogen)
24. Dawei Gao, Zitao Li, Xuchen Pan, Weirui Kuang, Zhijian Ma, Bingchen Qian, Fei Wei, Wenhao Zhang, Yuexiang Xie, Daoyuan Chen, Liuyi Yao, Hongyi Peng, Zeyu Zhang, Lin Zhu, Chen Cheng, Hongzhu Shi, Yaliang Li, Bolin Ding, and Jingren Zhou. Agentscope: A flexible yet robust multi-agent platform, 2024. U… — [arXiv:2402.14034](https://arxiv.org/abs/2402.14034) [find](https://scholar.google.com/scholar?q=Dawei+Gao%2C+Zitao+Li%2C+Xuchen+Pan%2C+Weirui+Kuang%2C+Zhijian+Ma%2C+Bingchen+Qian%2C+Fei+Wei%2C+Wenhao+Zhang%2C+Yuexiang+Xie%2C+Daoyuan+Chen%2C+Liuyi+Yao%2C+Hongyi+Peng%2C+Zeyu+Zhang%2C+Lin+Zhu%2C+Chen+Cheng%2C+Hongzhu+Shi%2C+Yalia)
25. Yixuan Weng, Minjun Zhu, Guangsheng Bao, Hongbo Zhang, Jindong Wang, Yue Zhang, and Linyi Yang. [Cycleresearcher: Improving automated research via automated review](https://md.research.elamur.ai/free/en/papers/weng-2024-cycleresearcher-improving-automated-research/), 2025. URL https://arxiv.org/abs/2411.00816. [↗](https://arxiv.org/abs/2411.00816)
26. AI Co-Scientist Team. Towards an ai co-scientist. [https://storage.googleapis.com/](https://storage.googleapis.com/) coscientist_paper/ai_coscientist.pdf, 2025. [↗](https://storage.googleapis.com/)
27. 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/), 2025. URL https://arxiv.org/abs/2501.04227. [↗](https://arxiv.org/abs/2501.04227)

*Updated 3 November 2026*