# GPT-Lab: Next Generation Of Optimal Chemistry Discovery By GPT Driven Robotic Lab

arXiv: https://arxiv.org/abs/2309.16721 · HTML: https://mlsanity.com/paper/2309.16721/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 6 of 6)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [Emergent autonomous scientific research capabilities of large language models](https://mlsanity.com/paper/2304.05332/) (2023)
- [Predicting Research Trends with Semantic and Neural Networks with an application in Quantum Physics](https://mlsanity.com/paper/1906.06843/) (2019)

## Built on by (most cited first, 3 of 3)

- [From Words to Molecules: A Survey of Large Language Models in Chemistry](https://mlsanity.com/paper/2402.01439/) (2024)
- [Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Research](https://mlsanity.com/paper/2506.12312/) (2025)
- [Speculative Exploration on the Concept of Artificial Agents Conducting Autonomous Research](https://mlsanity.com/paper/2312.03497/) (2023)

## Abstract (arXiv)

The integration of robots in chemical experiments has enhanced experimental efficiency, but lacking the human intelligence to comprehend literature, they seldom provide assistance in experimental design. Therefore, achieving full-process autonomy from experiment design to validation in self-driven laboratories (SDL) remains a challenge. The introduction of Generative Pre-trained Transformers (GPT), particularly GPT-4, into robotic experimentation offers a solution. We introduce GPT-Lab, a paradigm that employs GPT models to give robots human-like intelligence. With our robotic experimentation platform, GPT-Lab mines literature for materials and methods and validates findings through high-throughput synthesis. As a demonstration, GPT-Lab analyzed 500 articles, identified 18 potential reagents, and successfully produced an accurate humidity colorimetric sensor with a root mean square error (RMSE) of 2.68%. This showcases the rapid materials discovery and validation potential of our system.