Template-guided interpretable reasoning with execution feedback for LLM-based program repair

Sichong Hao

doi:10.1016/j.infsof.2026.108058

Template-guided interpretable reasoning with execution feedback for LLM-based program repair

2026-01-28

0

PRE

AI

DOI：10.1016/j.infsof.2026.108058

Original

Original request for help

Save

Abstract

En 中文

Automated Program Repair (APR) seeks to fix software defects automatically. Large language models (LLMs) show promise in APR, especially when combined with traditional template-based methods. However, existing approaches suffer from low accuracy, poor interpretability, and incompatibility with mainstream closed-source LLMs, leaving the synergy between traditional methods and LLMs underexplored.

Template-guided interpretable reasoning with execution feedback for LLM-based program repair

Abstract

Journal

Organization