作者位次 #2/5ACL 2026Findings· Findings of ACL
S ynth F ix: Adaptive Neuro-Symbolic Code Vulnerability Repair
Yifan Zhang · Jieyu Li · Kexin Pei · Yu Huang · Kevin Leach
摘要
Large Language Models (LLMs) show promise for automated code repair but often struggle with the complex semantic and structural correctness required. We present SynthFix, a hybrid neural-symbolic framework that improves LLM-based vulnerability repair by unifying code synthesis with compiler-infor...