This paper presents a systematic literature review on the application of Large Language Models (LLMs) in Automated Program Repair (APR) from 2020 to 2024. The authors, from various institutions in China, Singapore, and Australia, analyze 127 relevant papers to provide an overview of the current achievements, challenges, and potential opportunities in LLM-based APR. The review categorizes popular LLMs used in APR, outlines three types of utilization strategies, and details specific repair scenarios such as semantic bugs and security vulnerabilities. The paper also discusses critical aspects of integrating LLMs into APR, including input forms and open science. Finally, it highlights remaining challenges and potential guidelines for future research. The authors aim to bridge the gap in understanding the current state of LLM-based APR and provide a comprehensive overview to aid researchers in advancing this field. The artifacts of the study are publicly available on GitHub.This paper presents a systematic literature review on the application of Large Language Models (LLMs) in Automated Program Repair (APR) from 2020 to 2024. The authors, from various institutions in China, Singapore, and Australia, analyze 127 relevant papers to provide an overview of the current achievements, challenges, and potential opportunities in LLM-based APR. The review categorizes popular LLMs used in APR, outlines three types of utilization strategies, and details specific repair scenarios such as semantic bugs and security vulnerabilities. The paper also discusses critical aspects of integrating LLMs into APR, including input forms and open science. Finally, it highlights remaining challenges and potential guidelines for future research. The authors aim to bridge the gap in understanding the current state of LLM-based APR and provide a comprehensive overview to aid researchers in advancing this field. The artifacts of the study are publicly available on GitHub.