---
title: "Emergent autonomous scientific research capabilities of large"
description: "The authors build an LLM-driven \"Agent\" whose central GPT-4 Planner coordinates several helper… 18 references, cited by 56 papers here."
authors: ["Daniil A. Boiko", "Robert MacKnight", "Gabe Gomes"]
year: 2023
venue: "arXiv:2304.05332 · published as \"Autonomous chemical research with large language models\", Nature (2023), doi:10.1038/s41586-023-06792-0"
source: "https://arxiv.org/abs/2304.05332"
doi: "10.48550/arxiv.2304.05332"
arxiv: "2304.05332"
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/boiko-2023-emergent-autonomous-scientific-research/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/boiko-2023-emergent-autonomous-scientific-research/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/6/) / Emergent autonomous scientific research capabilities of large language models

# Emergent autonomous scientific research capabilities of large language models

**Authors:** [Daniil A. Boiko](https://md.research.elamur.ai/free/en/authors/daniil-a-boiko/), [Robert MacKnight](https://md.research.elamur.ai/free/en/authors/robert-macknight/) and [Gabe Gomes](https://md.research.elamur.ai/free/en/authors/gabe-gomes/) · **Year:** 2023 · **Venue:** arXiv:2304.05332 · published as "Autonomous chemical research with large language models", Nature (2023), doi:10.1038/s41586-023-06792-0 · **Licence:** [arXiv non-exclusive distribution license](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2304.05332) · [PDF](https://arxiv.org/pdf/2304.05332) · [DOI 10.48550/arxiv.2304.05332](https://doi.org/10.48550/arxiv.2304.05332) · [arXiv 2304.05332](https://arxiv.org/abs/2304.05332) · [OpenAlex](https://openalex.org/W4365211632)

**Citations:** 72 citations (OpenAlex, 2026-10-14) · [56](https://md.research.elamur.ai/free/en/papers/boiko-2023-emergent-autonomous-scientific-research/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks whether large language models can do more than answer chemistry questions and instead run experimental research largely on their own. The authors build an LLM-driven "Agent" whose central GPT-4 Planner coordinates several helper modules. These modules handle Google-based web search (summarised by GPT-3.5), retrieval over hardware documentation, sandboxed Python execution in Docker, and an automation layer that sends generated code to lab equipment. To get around GPT-4's September 2021 knowledge cutoff, documentation is supplied at run time through embedding-based search or through summarised function guides. The system plans syntheses of common drugs, finds the right functions in an unfamiliar cloud-lab language, and steers an Opentrons liquid handler from plain-language instructions. Its hardest task combines several instruments to carry out palladium-catalysed cross-coupling reactions, and GC-MS confirms the products. The work shows that general-purpose LLMs connected to tools can close the loop from planning to physical experiment, which raises both opportunities and misuse concerns. The authors examine these risks and suggest safeguards.

## Key points
- **Architecture:** a Planner chooses among four actions (GOOGLE, PYTHON, DOCUMENTATION, EXPERIMENT). Code and instrument outputs are fed back so the Planner can fix its own errors.
- **Documentation retrieval:**
  - For the OT-2 Python API, ada embeddings were built for all 14 documentation sections, and relevant sections are selected by vector distance within a 7,800-token budget.
  - For Emerald Cloud Lab's Symbolic Lab Language (SLL), which GPT-4 did not know, a separate GPT-4 model condenses the function documentation.
- **Synthesis planning:**
  - For ibuprofen, the Agent correctly proposed the opening Friedel-Crafts acylation step.
  - Aspirin was planned well.
  - The aspartame plan omitted the methyl group.
- **UV-Vis task:** the Agent located red, yellow and blue samples on a plate from their absorbance maxima (530, 430 and 630 nm).
- **Cross-coupling:** the Agent executed Suzuki and Sonogashira reactions, and GC-MS showed product peaks at m/z 154 and 178. The Nature version names the system Coscientist.

*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

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 598 works · 191,226 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🧱 Materials Science](https://md.research.elamur.ai/free/en/shelves/materials-science/) · 31 works · [🧱 Materials Chemistry](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/) · 31 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Daniil A. Boiko, Robert MacKnight and Gabe Gomes. 2023. Emergent autonomous scientific research capabilities of large language models. arXiv:2304.05332 · published as "Autonomous chemical research with large language models", Nature (2023), doi:10.1038/s41586-023-06792-0.

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

```bibtex
@misc{boiko2023emergent,
  title = {{Emergent autonomous scientific research capabilities of large language models}},
  author = {Daniil A. Boiko, Robert MacKnight and Gabe Gomes},
  year = {2023},
  doi = {10.48550/arxiv.2304.05332},
  eprint = {2304.05332},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2304.05332}
}
```

- [← previous Code4Struct: Code Generation for Few-Shot Event Structure Prediction](https://md.research.elamur.ai/free/en/papers/wang-2023-code4struct-code-generation-few-shot/)
- [next → ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://md.research.elamur.ai/free/en/papers/xu-2023-expertprompting-instructing-large-language-models/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/6/)

## References

18 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Brown, T. et al. [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). in Advances in Neural Information Processing Systems (eds. Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. F. & Lin, H.) vol. 33 1877–1901 (Curran Associates, Inc., 2020).
2. Thoppilan, R. et al. [LaMDA: Language Models for Dialog Applications](https://md.research.elamur.ai/free/en/papers/thoppilan-2022-lamda-language-models-dialog-applications/). (2022).
3. Touvron, H. et al. [LLaMA: Open and Efficient Foundation Language Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). (2023).
4. Hoffmann, J. et al. [Training Compute-Optimal Large Language Models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/). (2022).
5. Chowdhery, A. et al. [PaLM: Scaling Language Modeling with Pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). (2022).
6. Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science (1979) 379, 1123–1130 (2023). [find](https://scholar.google.com/scholar?q=Lin%2C+Z%2E+et+al%2E+Evolutionary%2Dscale+prediction+of+atomic%2Dlevel+protein+structure+with+a+language+model%2E+Science+%281979%29+379%2C+1123%E2%80%931130+%282023%29%2E)
7. Luo, R. et al. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Brief Bioinform 23, (2022). [find](https://scholar.google.com/scholar?q=Luo%2C+R%2E+et+al%2E+BioGPT%3A+generative+pre%2Dtrained+transformer+for+biomedical+text+generation+and+mining%2E+Brief+Bioinform+23%2C+%282022%29%2E)
8. Irwin, R., Dimitriadis, S., He, J. & Bjerrum, E. J. Chemformer: a pre-trained transformer for computational chemistry. Mach Learn Sci Technol 3, 015022 (2022). [find](https://scholar.google.com/scholar?q=Irwin%2C+R%2E%2C+Dimitriadis%2C+S%2E%2C+He%2C+J%2E+%26+Bjerrum%2C+E%2E+J%2E+Chemformer%3A+a+pre%2Dtrained+transformer+for+computational+chemistry%2E+Mach+Learn+Sci+Technol+3%2C+015022+%282022%29%2E)
9. Kim, H., Na, J. & Lee, W. B. Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention. J Chem Inf Model 61, 5804–5814 (2021). [find](https://scholar.google.com/scholar?q=Kim%2C+H%2E%2C+Na%2C+J%2E+%26+Lee%2C+W%2E+B%2E+Generative+Chemical+Transformer%3A+Neural+Machine+Learning+of+Molecular+Geometric+Structures+from+Chemical+Language+via+Attention%2E+J+Chem+Inf+Model+61%2C+5804%E2%80%935814+%282021%29%2E)
10. OpenAI. [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). (2023).
11. Ziegler, D. M. et al. Fine-Tuning Language Models from Human Preferences. (2019). [find](https://scholar.google.com/scholar?q=Ziegler%2C+D%2E+M%2E+et+al%2E+Fine%2DTuning+Language+Models+from+Human+Preferences%2E+%282019%29%2E)
12. 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).
13. Bran, A. M., Cox, S., White, A. D. & Schwaller, P. [ChemCrow: Augmenting large-language models with chemistry tools](https://md.research.elamur.ai/free/en/papers/bran-2023-chemcrow-augmenting-large-language/). (2023).
14. Reaxys. [https://www.reaxys.com](https://www.reaxys.com). [↗](https://www.reaxys.com)
15. SciFinder. [https://scifinder.cas.org](https://scifinder.cas.org). [↗](https://scifinder.cas.org)
16. Opentrons. Opentrons Python Protocol API. [https://docs.opentrons.com/v2/](https://docs.opentrons.com/v2/). [↗](https://docs.opentrons.com/v2/)
17. Emerald Cloud Lab. Running [https://www.emeraldcloudlab.com/guides/runningexperiments](https://www.emeraldcloudlab.com/guides/runningexperiments). Experiments. [↗](https://www.emeraldcloudlab.com/guides/runningexperiments)
18. Urbina, F., Lentzos, F., Invernizzi, C. & Ekins, S. Dual use of artificial-intelligence-powered drug discovery. Nat Mach Intell 4, 189–191 (2022). [find](https://scholar.google.com/scholar?q=Urbina%2C+F%2E%2C+Lentzos%2C+F%2E%2C+Invernizzi%2C+C%2E+%26+Ekins%2C+S%2E+Dual+use+of+artificial%2Dintelligence%2Dpowered+drug+discovery%2E+Nat+Mach+Intell+4%2C+189%E2%80%93191+%282022%29%2E)

*Updated 2 November 2026*