Autonomous chemical research with large language models

By Daniil A. Boiko, Robert MacKnight, Benjamin C Kline, Gabe Gomes. Nature, 2023

1,096 citations recorded by the source corpus.

Transformer-based large language models are making significant strides in various fields, such as natural language processing^ 1 – 5 , biology^ 6 , 7 , chemistry^ 8 – 10 and computer programming^ 11 , 12 . Here, we show the development and capabilities of Coscientist, an artificial intelligence system driven by GPT-4 that autonomously designs, plans and performs complex experiments by incorporating large language models empowered by tools such as internet and documentation search, code execution and experimental automation. Coscientist showcases its potential for accelerating research across six diverse tasks, including the successful reaction optimization of palladium-catalysed cross-couplings, while exhibiting advanced capabilities for (semi-)autonomous experimental design and execution. Our findings demonstrate the versatility, efficacy and explainability of artificial intelligence systems like Coscientist in advancing research. Coscientist is an artificial intelligence system driven by GPT-4 that autonomously designs, plans and performs experiments by incorporating large language models empowered by tools such as internet and documentation search, code execution and experimental automation.

Subfields: Biomedical Engineering, Electrical and Electronic Engineering, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/6fe3779fe5f2e9402abdd08ad8db41a0f13a99eb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Electrical and Electronic Engineering

In Materials Chemistry

Citations in the corpus

Artificial intelligence in drug development (2025, positive): “246), we can be judiciously optimistic about AI’s promise for accelerating drug development and benefiting human health.”
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning (2024, background): “Moreover, LLMs can assist users in synthesizing dangerous chemicals (Boiko et al., 2023) or conducting cyberattacks (Bhatt et al., 2023).”
AlphaEvolve: A coding agent for scientific and algorithmic discovery (2025, positive): “Other works use LLMs to optimize experimental planning and design [7, 10, 43, 75] or experiment execution and workflow [28, 62, 82, 105, 116].”
Empowering Biomedical Discovery with AI Agents (2024, positive): “AI agents can break down a problem into manageable subtasks, which can then be addressed by agents with specialized functions for targeted problem-solving and integration of scientiﬁc knowledge [1, 5].”
OpenHands: An Open Platform for AI Software Developers as Generalist Agents (2024, positive): “They are moving towards performing complex tasks such as developing software (Jimenez et al., 2024), navigating real-world websites (Zhou et al., 2023a), doing household chores (Ahn et al., 2022), or even performing scientific research (Boiko et al., 2023; Tang et al., 2024a).”