PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices

2026-06-16

AI Summary

Current large language model (LLM)-based automated program repair approaches fail to effectively leverage dynamic execution information—such as failure traces and fine-grained validation feedback—thereby limiting their repair performance. This work proposes PracRepair, a novel framework that systematically integrates human-like debugging practices into the LLM repair pipeline for the first time. PracRepair jointly utilizes static code and dynamic execution context to generate problem-driven repair hypotheses and iteratively refines patches based on trace-level behavioral changes and validation diagnostics. Evaluated on Defects4J V1.2 and V2.0, PracRepair successfully repairs 162 and 171 bugs, respectively, using GPT-4o, substantially outperforming existing methods. Moreover, it demonstrates strong generalization capability on the real-world benchmark RWB dataset.

Abstract

As software systems grow in scale and complexity, debugging and repair remain costly and time-consuming. Large language models (LLMs) have advanced automated program repair (APR), but existing LLM-based APR approaches still largely rely on static or retrieved context, error messages, and coarse-grained validation outcomes. As a result, they underutilize dynamic information for failure understanding and repair, including failure-execution dynamics and patch-validation dynamics. Effectively leveraging such information, however, is challenging: failure-execution traces are large and noisy, raw static-dynamic context is not self-explanatory, and patch-validation dynamics are often reduced to coarse feedback. To address these challenges, we propose \textsc{PracRepair}, a fully automated LLM-based APR framework inspired by human-like debugging practices. \textsc{PracRepair} constructs an on-demand static-dynamic context from buggy programs and failure executions, performs question-driven failure diagnosis to formulate explicit repair hypotheses, and iteratively refines candidate patches using validation diagnostics and trace-level behavioral changes. Experimental results on Defects4J V1.2 and V2.0 show that \textsc{PracRepair} consistently outperforms state-of-the-art baselines. Specifically, under GPT-3.5, \textsc{PracRepair} correctly fixes 139/136 bugs on Defects4J V1.2/V2.0, while under GPT-4o it further improves to 162/171. Moreover, \textsc{PracRepair} generalizes effectively to RWB (Real-World Bugs), achieving the best performance across multiple foundation models.

Problem

• Automated Program Repair
• Large Language Models
• Dynamic Information
• Failure Diagnosis
• Patch Validation

Innovation

• Automated Program Repair
• Large Language Models
• Dynamic Execution Traces
• Failure Diagnosis
• Patch Validation