作者位次 #4/7ACL 2026Findings· Findings of ACL
Code Reffix: A Benchmark for Reflection-Guided Code Repair with Large Language Models
Zaiyuan Di · Jianting Chen · Yunxiao Yang · Xiaoying Gao · Li Yang · Zhihao Wang · Yang Xiang
摘要
While recent studies have increasingly emphasized the role of reflection in code repair tasks, existing benchmarks still target the repair generation capability of LLMs, lacking fine-grained evaluation of reflection generation capability. To this end, we propose Code Reffix, a benchmark featuring...