This review explores the integration of Large Language Models (LLMs) and autonomous agents in chemistry, highlighting their potential to accelerate scientific discovery through automation. LLMs have emerged as powerful tools in various aspects of chemistry, including molecule design, property prediction, and synthesis optimization. The 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. Future directions point towards more sophisticated multi-modal agents and enhanced collaboration between agents and experimental methods. The review also discusses the use of LLMs in autonomous agents, which perform tasks such as paper scraping, interfacing with automated laboratories, and synthesis planning. These agents are designed to interact with their environment using a broader set of tools, making them versatile and capable of performing a wide range of tasks. The review is structured into several sections, covering the introduction of LLMs, their training, and various applications in chemistry. It also delves into the challenges and opportunities in chemistry, emphasizing the importance of trustworthy datasets and good benchmarks. The review concludes with a discussion on the future of LLMs and autonomous agents in chemistry, highlighting the potential for these technologies to revolutionize the field.This review explores the integration of Large Language Models (LLMs) and autonomous agents in chemistry, highlighting their potential to accelerate scientific discovery through automation. LLMs have emerged as powerful tools in various aspects of chemistry, including molecule design, property prediction, and synthesis optimization. The 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. Future directions point towards more sophisticated multi-modal agents and enhanced collaboration between agents and experimental methods. The review also discusses the use of LLMs in autonomous agents, which perform tasks such as paper scraping, interfacing with automated laboratories, and synthesis planning. These agents are designed to interact with their environment using a broader set of tools, making them versatile and capable of performing a wide range of tasks. The review is structured into several sections, covering the introduction of LLMs, their training, and various applications in chemistry. It also delves into the challenges and opportunities in chemistry, emphasizing the importance of trustworthy datasets and good benchmarks. The review concludes with a discussion on the future of LLMs and autonomous agents in chemistry, highlighting the potential for these technologies to revolutionize the field.