Can AI Fix Buggy Code? Exploring the Use of Large Language Models in Automated Program Repair

2025/06/26 by Lan Zhang, Anoop Singhal, Qingtian Zou +3
Computer Science · Decision Sciences · #Software Engineering Research #Scientific Computing and Data Management

paper · doi:10.1109/mc.2025.3527407

Abstract

This article reviews the current human–large language models collaboration approach to bug fixing and points out the research directions toward (the development of) autonomous program repair artificial intelligence agents.

Related

• A Comprehensive Survey of AI-Driven Advancements and Techniques in Automated Program Repair and Code Generation
• Do AI models help produce verified bug fixes?
• RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
• Empirical Evaluation of Large Language Models in Automated Program Repair
• MarsCode Agent: AI-native Automated Bug Fixing