---
title: "StarWhisper Telescope — paper by Wang et al. (2024)"
description: "Large time-domain telescope arrays generate heavy routine workloads. 42 references, cited by 5 papers here."
authors: ["Cunshi Wang", "Yu Zhang", "Yuyang Li", "Xinjie Hu", "Yiming Mao", "Xunhao Chen", "Pengliang Du", "Rui Wang", "Ying Wu", "Hang Yang", "Yansong Li", "Beichuan Wang", "Haiyang Mu", "Zheng Wang", "Jianfeng Tian", "Liang Ge", "Yongna Mao", "Shengming Li", "Xiaomeng Lu", "Jinhang Zou", "Yang Huang", "Ningchen Sun", "Jie Zheng", "Min He", "Yu Bai", "Junjie Jin", "Hong Wu", "Jifeng Liu"]
year: 2024
venue: "arXiv:2412.06412"
source: "https://arxiv.org/abs/2412.06412"
doi: "10.48550/arxiv.2412.06412"
arxiv: "2412.06412"
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/wang-2024-starwhisper-telescope-ai-framework-automating/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2024-starwhisper-telescope-ai-framework-automating/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/12/) / StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations

# StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations

**Authors:** Cunshi Wang, [Yu Zhang](https://md.research.elamur.ai/free/en/authors/yu-zhang/), Yuyang Li, Xinjie Hu, Yiming Mao, Xunhao Chen, Pengliang Du, [Rui Wang](https://md.research.elamur.ai/free/en/authors/rui-wang/), Ying Wu, Hang Yang, Yansong Li, Beichuan Wang, Haiyang Mu, [Zheng Wang](https://md.research.elamur.ai/free/en/authors/zheng-wang/), Jianfeng Tian, Liang Ge, Yongna Mao, Shengming Li, Xiaomeng Lu, Jinhang Zou, Yang Huang, Ningchen Sun, Jie Zheng, Min He, [Yu Bai](https://md.research.elamur.ai/free/en/authors/yu-bai/), Junjie Jin, Hong Wu and Jifeng Liu · **Year:** 2024 · **Venue:** arXiv:2412.06412 · **Publisher:** [Springer Science+Business Media](https://md.research.elamur.ai/free/en/publishers/springer-science-business-media/) · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2412.06412) · [PDF](https://arxiv.org/pdf/2412.06412) · [DOI 10.48550/arxiv.2412.06412](https://doi.org/10.48550/arxiv.2412.06412) · [arXiv 2412.06412](https://arxiv.org/abs/2412.06412) · [OpenAlex](https://openalex.org/W4415949988)

**Citations:** 14 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/wang-2024-starwhisper-telescope-ai-framework-automating/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary

Large time-domain telescope arrays generate heavy routine workloads. Staff must plan each night's targets for every site, run the instruments, and inspect large volumes of images for new transients. The authors address this with StarWhisper Telescope (SWT), an agent system built on the Qwen-2.5 language model. The model gains abilities through function calls and LLM-enhanced workflows that carry astronomical domain knowledge. A central agent coordinates four linked stages:

- **Planning:** building visibility-aware target lists for each telescope.
- **Control:** generating files for the N.I.N.A. control software.
- **Data processing:** image subtraction and transient detection.
- **Reporting:** automated messages that can add detected transients to later observation lists.

SWT was tested on the Nearby Galaxy Supernovae Survey (NGSS), a network of 10 amateur telescopes at several sites in China. There it found transients with response times the authors consider competitive with existing surveys. The work matters because a natural-language agent can replace much manual coordination. It also links amateur and professional observers and offers a template for running far larger arrays such as GOTTA.

## Key points

- **Target network:** GOTTA (also called SiTian) plans 60 one-meter telescopes in its first stage, mostly at Lenghu Observatory. Running it manually would need an estimated 200+ staff.
- **Manual workload:** planning means filtering a catalog of more than 100,000 objects. Review involves about 20 GB of raw images per telescope.
- **NGSS setup:** 10 telescopes, 7 at Xinglong and one each in Gansu, Yunnan and Xinjiang. All have apertures under 250 mm, monochrome CMOS sensors and LRGB filters. The survey targets galaxies within 50 Mpc and covers more than 500 fields (about 3,000+ galaxies) on a clear night.
- **Control chain:** SWT writes ninaTargetSet files for N.I.N.A., which operates the hardware through ASCOM drivers. Subtraction images come from the X-OPSTEP pipeline.
- **Domain grounding:** the authors note that off-the-shelf LLMs (Qwen, GPT, DeepSeek) tend to suggest famous objects even when those objects are not observable. SWT's tool integration is designed to correct this.

*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

- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 256 works · 25,136 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 196 works · 8,907 citations
- [Simon Fraser University](https://md.research.elamur.ai/free/en/universities/simon-fraser-university/) — University, Burnaby, Canada · 21 works · 6,264 citations
- [Beijing Normal University](https://md.research.elamur.ai/free/en/universities/beijing-normal-university/) — University, Beijing, China · 23 works · 3,196 citations
- [Tibet University](https://md.research.elamur.ai/free/en/universities/tibet-university/) — University, Lhasa, China · 2 works · 26 citations

Also on the byline: [National Astronomical Observatories](https://ror.org/058pyyv44).

📚 Shelves (5): [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 206 works · [⚛️ Physics and Astronomy](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/) · 70 works · [⚙️ Computational Mechanics](https://md.research.elamur.ai/free/en/shelves/engineering/computational-mechanics/) · 8 works · [⚛️ Astronomy and Astrophysics](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/astronomy-and-astrophysics/) · 4 works · [⚛️ Instrumentation](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/instrumentation/) · 2 works

## Cite

Cite as: Cunshi Wang, Yu Zhang, Yuyang Li, Xinjie Hu, Yiming Mao, Xunhao Chen, Pengliang Du, Rui Wang, Ying Wu, Hang Yang, Yansong Li, Beichuan Wang, Haiyang Mu, Zheng Wang, Jianfeng Tian, Liang Ge, Yongna Mao, Shengming Li, Xiaomeng Lu, Jinhang Zou, Yang Huang, Ningchen Sun, Jie Zheng, Min He, Yu Bai, Junjie Jin, Hong Wu and Jifeng Liu. 2024. StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations. arXiv:2412.06412.

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

```bibtex
@misc{wang2024starwhisper,
  title = {{StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations}},
  author = {Cunshi Wang, Yu Zhang, Yuyang Li, Xinjie Hu, Yiming Mao, Xunhao Chen, Pengliang Du, Rui Wang, Ying Wu, Hang Yang, Yansong Li, Beichuan Wang, Haiyang Mu, Zheng Wang, Jianfeng Tian, Liang Ge, Yongna Mao, Shengming Li, Xiaomeng Lu, Jinhang Zou, Yang Huang, Ningchen Sun, Jie Zheng, Min He, Yu Bai, Junjie Jin, Hong Wu and Jifeng Liu},
  year = {2024},
  doi = {10.48550/arxiv.2412.06412},
  eprint = {2412.06412},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2412.06412}
}
```

- [← previous sDPO: Don't Use Your Data All at Once](https://md.research.elamur.ai/free/en/papers/kim-2024-sdpo-don-t-use-data/)
- [next → Suri: Multi-constraint Instruction Following in Long-form Text Generation](https://md.research.elamur.ai/free/en/papers/pham-2024-suri-multi-constraint-instruction-following/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/12/)

## References

42 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Liu, J., Soria, R., Wu, X.-F., Wu, H. & Shang, Z. The SiTian Project. Anais da Academia Brasileira de Ciencias 93, 20200628 (2021). [find](https://scholar.google.com/scholar?q=Liu%2C+J%2E%2C+Soria%2C+R%2E%2C+Wu%2C+X%2E%2DF%2E%2C+Wu%2C+H%2E+%26+Shang%2C+Z%2E+The+SiTian+Project%2E+Anais+da+Academia+Brasileira+de+Ciencias+93%2C+20200628+%282021%29%2E)
2. Huang, Y. et al. The mini-sitian array: A pathfinder for the sitian project (2025). URL https://arxiv.org/abs/2504.01615. 2504.01615. — [arXiv:2504.01615](https://arxiv.org/abs/2504.01615) [↗](https://arxiv.org/abs/2504.01615)
3. Wang, Z. et al. The mini-sitian array: Design and application of master control system. Research in Astronomy and Astrophysics 25, 044004 (2025). URL http://dx.doi.org/10.1088/1674-4527/adc78e. \\\#User Prompt: I need to import the observation list, Xinglong Station, November 27, 2024, Telescope 1. \\… — [doi:10.1088/1674-4527/adc78e](https://doi.org/10.1088/1674-4527/adc78e) [↗](http://dx.doi.org/10.1088/1674-4527/adc78e)
4. Gu, H. et al. The mini-sitian array: the mini-sitian realtime image processing pipeline (strip) (2025). URL https://arxiv.org/abs/2504.01609. 2504.01609. — [arXiv:2504.01609](https://arxiv.org/abs/2504.01609) [↗](https://arxiv.org/abs/2504.01609)
5. Ouyang, L. et al. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/) (2022). URL https://arxiv.org/abs/2203.02155. 2203.02155. [↗](https://arxiv.org/abs/2203.02155)
6. Carroll Wainwright, R. L. Instructgpt: [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). [https://github.com/openai/](https://github.com/openai/) following-instructions-human-feedback (2022). [↗](https://github.com/openai/)
7. Bai, J. et al. Qwen technical report (2023). URL https://arxiv.org/abs/2309. 16609. 2309.16609. [↗](https://arxiv.org/abs/2309)
8. Yang, A. et al. Qwen2 technical report (2024). URL https://arxiv.org/abs/2407. 10671. 2407.10671. [↗](https://arxiv.org/abs/2407)
9. OpenAI et al. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/) (2024). URL https://arxiv.org/abs/2303. 08774. 2303.08774. [↗](https://arxiv.org/abs/2303)
10. DeepSeek-AI et al. Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model (2024). URL https://arxiv.org/abs/2405.04434. 2405. 04434. [↗](https://arxiv.org/abs/2405.04434)
11. Andreas, J. Language models as agent models (2022). URL [https://arxiv.org/](https://arxiv.org/) abs/2212.01681. 2212.01681. — [arXiv:2212.01681](https://arxiv.org/abs/2212.01681) [↗](https://arxiv.org/)
12. Qin, Y. et al. [Toolllm: Facilitating large language models to master 16000+ real-world apis](https://md.research.elamur.ai/free/en/papers/qin-2023-toolllm-facilitating-large-language-models/) (2023). URL https://arxiv.org/abs/2307.16789. 2307.16789. [↗](https://arxiv.org/abs/2307.16789)
13. Wang, X. et al. [Mint: Evaluating llms in multi-turn interaction with tools and language feedback](https://md.research.elamur.ai/free/en/papers/wang-2023-mint-evaluating-llms-multi-turn/) (2024). URL https://arxiv.org/abs/2309.10691. 2309.10691. [↗](https://arxiv.org/abs/2309.10691)
14. Sinha, N., Jain, V. & Chadha, A. Evaluating open language models across task types, application domains, and reasoning types: An in-depth experimental analysis (2024). URL https://arxiv.org/abs/2406.11402. 2406.11402. [↗](https://arxiv.org/abs/2406.11402)
15. Qian, L. et al. langchain-chatchat. GitHub repository (2024). URL [https://github.com/chatchat-space/Langchain-Chatchat](https://github.com/chatchat-space/Langchain-Chatchat). [↗](https://github.com/chatchat-space/Langchain-Chatchat)
16. Qian, C. et al. [Experiential co-learning of software-developing agents](https://md.research.elamur.ai/free/en/papers/qian-2023-experiential-co-learning-software/) (2024). URL https://arxiv.org/abs/2312.17025. 2312.17025. [↗](https://arxiv.org/abs/2312.17025)
17. n8n. n8n - workflow automation. [https://github.com/n8n-io](https://github.com/n8n-io) (2022). [↗](https://github.com/n8n-io)
18. Wei, J. et al. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/) (2023). URL https://arxiv.org/abs/2201.11903. 2201.11903. [↗](https://arxiv.org/abs/2201.11903)
19. Ohlson, D., Seth, A., Gallo, E., Baldassare, V. & Greene, J. The 50 mpc galaxy catalog (50 mgc): Consistent and homogeneous masses, distances, colors, and morphologies. Astronomical Journal 167 (2024). Publisher Copyright: © 2023. The Author(s). Published by the American Astronomical Society. [find](https://scholar.google.com/scholar?q=Ohlson%2C+D%2E%2C+Seth%2C+A%2E%2C+Gallo%2C+E%2E%2C+Baldassare%2C+V%2E+%26+Greene%2C+J%2E+The+50+mpc+galaxy+catalog+%2850+mgc%29%3A+Consistent+and+homogeneous+masses%2C+distances%2C+colors%2C+and+morphologies%2E+Astronomical+Journal+167+%282024%29)
20. Qwen. Qwen2.5. [https://github.com/QwenLM/Qwen2.5](https://github.com/QwenLM/Qwen2.5) (2024). [↗](https://github.com/QwenLM/Qwen2.5)
21. fmoraes74. nina-sites-plugin. [https://github.com/fmoraes74/nina-sites-plugin](https://github.com/fmoraes74/nina-sites-plugin) (2024). [↗](https://github.com/fmoraes74/nina-sites-plugin)
22. Chen, X. X-opstep. [https://github.com/Shinehope-Chen/X-OPSTEP](https://github.com/Shinehope-Chen/X-OPSTEP) (2024). [↗](https://github.com/Shinehope-Chen/X-OPSTEP)
23. Lang, D., Hogg, D. W., Mierle, K., Blanton, M. & Roweis, S. Astrometry.net: Blind astrometric calibration of arbitrary astronomical images. The Astronomical Journal 139, 1782 (2010). URL https://dx.doi.org/10.1088/0004-6256/139/5/ 1782. — [doi:10.1088/0004-6256/139/5/](https://doi.org/10.1088/0004-6256/139/5/) [find](https://scholar.google.com/scholar?q=Lang%2C+D%2E%2C+Hogg%2C+D%2E+W%2E%2C+Mierle%2C+K%2E%2C+Blanton%2C+M%2E+%26+Roweis%2C+S%2E+Astrometry%2Enet%3A+Blind+astrometric+calibration+of+arbitrary+astronomical+images%2E+The+Astronomical+Journal+139%2C+1782+%282010%29%2E+URL+https%3A%2F%2Fdx%2Edo)
24. Bertin, E. & Arnouts, S. Sextractor: Software for source extraction. Astron. Astrophys. Suppl. Ser. 117, 393–404 (1996). URL https://doi.org/10.1051/aas: 1996164. — [doi:10.1051/aas](https://doi.org/10.1051/aas) [↗](https://doi.org/10.1051/aas:)
25. Collaboration, G. et al. Gaia Data Release 3. Summary of the content and survey properties. Astronomy & Astrophysics 674, A1 (2023). [find](https://scholar.google.com/scholar?q=Collaboration%2C+G%2E+et+al%2E+Gaia+Data+Release+3%2E+Summary+of+the+content+and+survey+properties%2E+Astronomy+%26+Astrophysics+674%2C+A1+%282023%29%2E)
26. Bertin, E. et al. Bohlender, D. A., Durand, D. & Handley, T. H. (eds) The TERAPIX Pipeline. (eds Bohlender, D. A., Durand, D. & Handley, T. H.) Astronomical Data Analysis Software and Systems XI, Vol. 281 of Astronomical Society of the Pacific Conference Series, 228 (2002). [find](https://scholar.google.com/scholar?q=Bertin%2C+E%2E+et+al%2E+Bohlender%2C+D%2E+A%2E%2C+Durand%2C+D%2E+%26+Handley%2C+T%2E+H%2E+%28eds%29+The+TERAPIX+Pipeline%2E+%28eds+Bohlender%2C+D%2E+A%2E%2C+Durand%2C+D%2E+%26+Handley%2C+T%2E+H%2E%29+Astronomical+Data+Analysis+Software+and+Systems+XI%2C+Vol%2E)
27. Becker, A. HOTPANTS: High Order Transform of PSF ANd Template Subtraction. Astrophysics Source Code Library, record ascl:1504.004 (2015). [find](https://scholar.google.com/scholar?q=Becker%2C+A%2E+HOTPANTS%3A+High+Order+Transform+of+PSF+ANd+Template+Subtraction%2E+Astrophysics+Source+Code+Library%2C+record+ascl%3A1504%2E004+%282015%29%2E)
28. Shi, J.-H., Gu, H.-R., Huang, Y., Zhang, Y.-X. & Du, P.-L. The mini-sitian array: Real-bogus classification using deep learning. Research in Astronomy and Astrophysics 25, 044008 (2025). URL https://dx.doi.org/10.1088/1674-4527/ adc78b. — [doi:10.1088/1674-4527/](https://doi.org/10.1088/1674-4527/) [find](https://scholar.google.com/scholar?q=Shi%2C+J%2E%2DH%2E%2C+Gu%2C+H%2E%2DR%2E%2C+Huang%2C+Y%2E%2C+Zhang%2C+Y%2E%2DX%2E+%26+Du%2C+P%2E%2DL%2E+The+mini%2Dsitian+array%3A+Real%2Dbogus+classification+using+deep+learning%2E+Research+in+Astronomy+and+Astrophysics+25%2C+044008+%282025%29%2E+URL+https%3A%2F%2Fd)
29. Google. Agent2agent (a2a) protocol (2025). a2aproject/A2A. URL [https://github.com/](https://github.com/) [↗](https://github.com/)
30. Lewis, P. et al. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/) (2021). URL https://arxiv.org/abs/2005.11401. 2005.11401. [↗](https://arxiv.org/abs/2005.11401)
31. Hu, S., Ouyang, M., Gao, D. & Shou, M. Z. The dawn of gui agent: A preliminary case study with claude 3.5 computer use (2024). URL https://arxiv.org/abs/ 2411.10323. 2411.10323. [↗](https://arxiv.org/abs/)
32. DeepSeek-AI 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/) (2025). URL https://arxiv.org/abs/2501.12948. 2501. 12948. [↗](https://arxiv.org/abs/2501.12948)
33. GLM, T. et al. [Chatglm: A family of large language models from glm-130b to glm-4 all tools](https://md.research.elamur.ai/free/en/papers/glm-2024-chatglm-family-large-language-models/) (2024). URL https://arxiv.org/abs/2406.12793. 2406.12793. [↗](https://arxiv.org/abs/2406.12793)
34. Wang, H. et al. Scientific discovery in the age of artificial intelligence. Nature 620, 47–60 (2023). URL https://doi.org/10.1038/s41586-023-06221-2. [↗](https://doi.org/10.1038/s41586-023-06221-2)
35. agentscope. Agentscope. [https://github.com/modelscope/agentscope](https://github.com/modelscope/agentscope) (2023). [↗](https://github.com/modelscope/agentscope)
36. langgenius. Dify. [https://github.com/langgenius/dify](https://github.com/langgenius/dify) (2023). [↗](https://github.com/langgenius/dify)
37. Nguyen, D. V. et al. The simons observatory: Alarms and detector quality monitoring (2024). URL https://arxiv.org/abs/2406.14089. 2406.14089. — [arXiv:2406.14089](https://arxiv.org/abs/2406.14089) [↗](https://arxiv.org/abs/2406.14089)
38. Koopman, B. J. et al. The simons observatory: Deployment of the observatory control system and supporting infrastructure (2024). URL [https://arxiv.org/](https://arxiv.org/) abs/2406.15703. 2406.15703. — [arXiv:2406.15703](https://arxiv.org/abs/2406.15703) [↗](https://arxiv.org/)
39. Husser, T.-O. et al. pyobs – an observatory control system forrobotic telescopes (2022). URL https://arxiv.org/abs/2203.12642. 2203.12642. — [arXiv:2203.12642](https://arxiv.org/abs/2203.12642) [↗](https://arxiv.org/abs/2203.12642)
40. Silber, J. H. et al. The robotic multiobject focal plane system of the dark energy spectroscopic instrument (desi). The Astronomical Journal 165, 9 (2022). URL http://dx.doi.org/10.3847/1538-3881/ac9ab1. — [doi:10.3847/1538-3881/ac9ab1](https://doi.org/10.3847/1538-3881/ac9ab1) [↗](http://dx.doi.org/10.3847/1538-3881/ac9ab1)
41. Moss, A. [The ai cosmologist i: An agentic system for automated data analysis](https://md.research.elamur.ai/free/en/papers/moss-2025-ai-cosmologist-i-agentic-system/) (2025). URL https://arxiv.org/abs/2504.03424. 2504.03424. [↗](https://arxiv.org/abs/2504.03424)
42. He, M. et al. The mini-sitian array: First-two-year operation. Research in Astronomy and Astrophysics 25, 044005 (2025). URL http://dx.doi.org/10.1088/ 1674-4527/adc788. [find](https://scholar.google.com/scholar?q=He%2C+M%2E+et+al%2E+The+mini%2Dsitian+array%3A+First%2Dtwo%2Dyear+operation%2E+Research+in+Astronomy+and+Astrophysics+25%2C+044005+%282025%29%2E+URL+http%3A%2F%2Fdx%2Edoi%2Eorg%2F10%2E1088%2F+1674%2D4527%2Fadc788%2E)

*Updated 3 November 2026*