A review of large language models and autonomous agents in chemistry
Обзор больших языковых моделей и автономных агентов в химии
2024-12-09
SCID: 54.1/ydusgdzs
Discuss with AI
automated laboratoriesautonomous agentslarge language modelsmolecule designsynthesis planning
Figures from the paper
Abstract (AI)
Large language models (LLMs) have emerged as powerful tools in chemistry, significantly impacting molecule design, property prediction, and synthesis optimization. This review highlights LLM capabilities in these domains and their potential to accelerate scientific discovery through automation. We also review LLM-based autonomous agents: LLMs with a broader set of tools to interact with their surrounding environment. These agents perform diverse tasks such as paper scraping, interfacing with automated laboratories, and synthesis planning. As agents are an emerging topic, we extend the scope of our review of agents beyond chemistry and discuss across any scientific domains. This review covers the recent history, current capabilities, and design of LLMs and autonomous agents, addressing specific challenges, opportunities, and future directions in chemistry. Key challenges include data quality and integration, model interpretability, and the need for standard benchmarks, while future directions point towards more sophisticated multi-modal agents and enhanced collaboration between agents and experimental methods. Due to the quick pace of this field, a repository has been built to keep track of the latest studies: https://github.com/ur-whitelab/LLMs-in-science.
Key Findings
1
Autonomous-agent applications are reviewed across scientific domains because this emerging technology extends beyond chemistry.
2
Future progress is expected from multimodal agents and stronger integration between autonomous agents and experimental methods; a repository tracks rapidly developing research.
3
Key obstacles include data quality and integration, limited model interpretability, and the absence of standardized benchmarks.
4
LLM-based autonomous agents extend language models with tools for tasks including literature scraping, automated-laboratory interaction, and synthesis planning.
5
Large language models are significantly affecting molecular design, property prediction, and synthesis optimization in chemistry.
Research Object
large language models and LLM-based autonomous agents in chemistry and other scientific domains
Research Subject
their capabilities, applications, design, challenges, and future directions for molecule design, property prediction, synthesis optimization, scientific information processing, laboratory interaction, and synthesis planning
Publication Details
Publication Date
2024-12-09
Journal
Publisher
ISSN
Cited by
274
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai20
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer2019
Neural Machine Translation by Jointly Learning to Align and Translate2014
A Comprehensive Survey on Graph Neural Networks2020
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules2018
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks2020
Robust Speech Recognition via Large-Scale Weak Supervision2022
MoleculeNet: a benchmark for molecular machine learning2017
A survey on large language model based autonomous agents2024
ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties2021
HuggingFace's Transformers: State-of-the-art Natural Language Processing2019
Generative Agents: Interactive Simulacra of Human Behavior2023
GPT-4 Technical Report2023
The blood–brain barrier: Structure, regulation and drug delivery2023
Evaluating Large Language Models Trained on Code2021
BioGPT: generative pre-trained transformer for biomedical text generation and mining2022
Autonomous chemical research with large language models2023
An autonomous laboratory for the accelerated synthesis of inorganic materials2023
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate2024
Structured information extraction from scientific text with large language models2024
Cited by7
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review2026
From language to action: a review of large language models as autonomous agents and tool users2026
Risks of AI scientists: prioritizing safeguarding over autonomy2025
Digital materials ecosystem: from databases to AI agents for autonomous discovery2026
AI agents in drug discovery: applications and case studies2026
SasAgent : multi-agent artificial intelligence system for small-angle scattering data analysis2026
Toward autonomous chemical discovery: agentic AI in organic synthesis and nanochemistry2026