logo
ResearchBunny Logo
Abstract
This paper introduces Coscientist, an AI system powered by GPT-4, capable of autonomously designing, planning, and executing complex chemical experiments. Coscientist leverages multiple LLMs and tools including internet and documentation search, code execution, and experimental automation. Its capabilities are demonstrated across six diverse tasks, including reaction optimization of palladium-catalyzed cross-couplings, showcasing its potential to accelerate scientific research.
Publisher
Nature
Published On
Dec 20, 2023
Authors
Daniil A. Boiko, Robert MacKnight, Ben Kline, Gabe Gomes
Tags
AI
chemical experiments
GPT-4
reaction optimization
scientific research
automation
cross-couplings

Related Publications

Explore these studies to deepen your understanding of the subject.

Accelerating materials language processing with large language models
Computer Science

Accelerating materials language processing with large language models

J. Choi and B. Lee

Large language models reveal big disparities in current wildfire research
Environmental Studies and Forestry

Large language models reveal big disparities in current wildfire research

Z. Lin, A. Chen, et al.

Leveraging molecular structure and bioactivity with chemical language models for de novo drug design
Chemistry

Leveraging molecular structure and bioactivity with chemical language models for de novo drug design

M. Moret, I. P. Angona, et al.

Automating psychological hypothesis generation with AI: when large language models meet causal graph
Psychology

Automating psychological hypothesis generation with AI: when large language models meet causal graph

S. Tong, K. Mao, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs—just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny