Autonomous chemical research with large language models
Автономные химические исследования с использованием больших языковых моделей
2023-12-20
SCID: 54.1/r4j4yxtm
Discuss with AI
CoscientistGPT-4autonomous experimental designexperimental automationpalladium-catalysed cross-couplings reaction optimization
Figures from the paper
Abstract (AI)
Abstract 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.
Key Findings
1
Coscientist accelerated research across six diverse tasks demonstrating versatility and efficacy in chemical research.
2
Coscientist exhibits advanced (semi-)autonomous experimental design and execution with explainable decision-making.
3
Coscientist integrates LLMs with tools including internet/documentation search, code execution, and experimental automation.
4
Coscientist successfully optimized a palladium-catalysed cross-coupling reaction, showing practical experimental success.
5
Coscientist, an AI system driven by GPT-4, autonomously designs, plans, and performs complex chemical experiments.
Research Object
Coscientist, an AI system driven by GPT-4 that autonomously designs, plans, and performs complex chemical experiments
Research Subject
The system's capabilities and performance in autonomous (and semi-autonomous) experimental design, planning, execution, and reaction optimization (including palladium-catalysed cross-couplings) enabled by LLMs and tool integration
Publication Details
Publication Date
2023-12-20
Journal
Publisher
ISSN
Cited by
1274
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
LLaMA: Open and Efficient Foundation Language Models2023
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing2022
Training language models to follow instructions with human feedback2022
PaLM: Scaling Language Modeling with Pathways2022
Scaling Laws for Neural Language Models2020
Sparks of Artificial General Intelligence: Early experiments with GPT-42023
BioGPT: generative pre-trained transformer for biomedical text generation and mining2022
Augmenting large language models with chemistry tools2024
Cited by20
A survey on large language model based autonomous agents2024
A Comprehensive Overview of Large Language Models2025
Augmenting large language models with chemistry tools2024
Self-Driving Laboratories for Chemistry and Materials Science2024
Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture2026
A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges2024
Empowering biomedical discovery with AI agents2024
Visibility into AI Agents2024
A multi-agent system for automating scientific discovery2026
Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects2026
A review of large language models and autonomous agents in chemistry2024
Autonomous ‘self-driving’ laboratories: a review of technology and policy implications2025
From language to action: a review of large language models as autonomous agents and tool users2026
Materials science in the era of large language models: a perspective2024
Towards end-to-end automation of AI research2026
AI, agentic models and lab automation for scientific discovery — the beginning of scAInce2025
Large‐Language‐Model‐Based AI Agent for Organic Semiconductor Device Research2024
Risks of AI scientists: prioritizing safeguarding over autonomy2025
Digital materials ecosystem: from databases to AI agents for autonomous discovery2026
Modular large language model agents for multi-task computational materials science2026