--- title: "Autonomous chemical research with large — Boiko 2023" description: "Boiko and colleagues examine how far large language models can go in carrying out real chemistry." authors: ["Daniil A. Boiko", "Robert MacKnight", "Ben Kline", "Gabe Gomes"] year: 2023 venue: "Nature" source: "https://doi.org/10.1038/s41586-023-06792-0" doi: "10.1038/s41586-023-06792-0" licence: "CC BY 4.0 (publisher, via OpenAlex)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/boiko-2023-autonomous-chemical-research-large-language/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/boiko-2023-autonomous-chemical-research-large-language/) [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/) / Autonomous chemical research with large language models # Autonomous chemical research with large language models **Authors:** Daniil A. Boiko, Robert MacKnight, Ben Kline, Gabe Gomes · **Year:** 2023 · **Venue:** Nature · **Licence:** [CC BY 4.0 (publisher, via OpenAlex)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://doi.org/10.1038/s41586-023-06792-0) · [PDF](https://www.nature.com/articles/s41586-023-06792-0.pdf) · [DOI 10.1038/s41586-023-06792-0](https://doi.org/10.1038/s41586-023-06792-0) · [OpenAlex](https://openalex.org/W4389991792) **Citations:** 1012 citations (openalex-snapshot · 2026-10-14) · [110](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Boiko and colleagues examine how far large language models can go in carrying out real chemistry. They ask what LLMs can contribute to the scientific process, how much autonomy is achievable, and whether an agent's choices can be inspected. Their answer is Coscientist, an agent built around a central GPT-4 "Planner." The Planner turns a plain-text request, such as running several Suzuki reactions, into steps and calls supporting tools: an LLM-driven web searcher, a sandboxed code runner, a documentation retriever, and an automation layer that sends instructions to lab hardware. The system was tested on six tasks. These range from planning syntheses of known compounds and learning hardware APIs to steering a liquid handler, combining several instruments and data sources, and optimizing reactions from previously collected results. In a synthesis-planning benchmark, connecting GPT-4 to web search clearly reduced invented or unworkable routes compared with standalone models. Coscientist also optimized conditions for palladium-catalysed cross-couplings. The work matters because it shows a general-purpose LLM, linked to search and robotics, moving from literature lookup to physical experiments while keeping its reasoning readable. ## Key points - **Architecture:** The Planner is a GPT-4 chat instance with four commands: GOOGLE, PYTHON, DOCUMENTATION and EXPERIMENT. Code runs inside an isolated Docker container, and the model can repair its own code when errors occur. - **Supported automation interfaces:** Coscientist controls Opentrons equipment via its Python API and also writes instructions in Emerald Cloud Lab's (ECL) Symbolic Lab Language (SLL). The hardware setup included a liquid handler, a heater–shaker module and UV-Vis measurements. - **Synthesis benchmark:** - Seven target compounds, including aspirin, acetaminophen, ibuprofen, nitroaniline and phenolphthalein, were scored on a 1–5 scale; scores below 3 counted as failure. - Baselines were GPT-3.5, GPT-4, Claude 1.3 and Falcon-40B-Instruct. - search-gpt-4 achieved top scores for four compounds and was the only system to reach an acceptable score for ibuprofen. - **Suggested extensions:** Adding reaction databases (Reaxys, SciFinder) or prompting strategies such as ReAct, Chain of Thought and Tree of Thoughts. - **Availability:** For safety reasons, the full code and prompts are withheld. A simplified implementation and the generated outputs are available at github.com/gomesgroup/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.* Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/) ## Cited by Cited by 110 papers of our library cite it (of the 140884 whose bibliographies we read); 5 of them have a page here, 105 not yet. - [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://md.research.elamur.ai/free/en/papers/cui-2023-chatlaw-multi-agent-legal-assistant/) - [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://md.research.elamur.ai/free/en/papers/novikov-2025-alphaevolve-coding-agent-scientific-algorithmic/) - [Agent Laboratory: Using LLM Agents as Research Assistants](https://md.research.elamur.ai/free/en/papers/schmidgall-2025-agent-laboratory-using-llm/) - [Meaning Representations as Variational Quantum Circuits](https://md.research.elamur.ai/free/en/papers/stokin-2026-meaning-representations-as-variational-quantum/) - [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/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{boiko2023autonomous, title = {{Autonomous chemical research with large language models}}, author = {Boiko, Daniil A. and MacKnight, Robert and Kline, Ben and Gomes, Gabe}, booktitle = {Nature}, year = {2023}, doi = {10.1038/s41586-023-06792-0}, url = {https://doi.org/10.1038/s41586-023-06792-0} } ``` - [← previous Automatic Standardization of Arabic Dialects for Machine Translation](https://md.research.elamur.ai/free/en/papers/alnassan-2023-automatic-standardization-arabic-dialects-machine/) - [next → Baichuan 2: Open Large-scale Language Models](https://md.research.elamur.ai/free/en/papers/yang-2023-baichuan-2-open-large-scale/) - [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/)