炒作与现实：LLM作为Simulink-Stateflow模型搜索式自动修复中的变异算子
原标题：Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models
AI 摘要
该研究将大语言模型（LLM）作为变异算子集成到基于搜索的自动程序修复（APR）中，用于Simulink-Stateflow模型。在19个真实故障模型上的受控评估中，LLM-based方法仅修复4-6个模型，而原始FlowRepair修复18个，表明LLM集成显著降低了修复性能。分析显示LLM在精确符号编辑上存在困难，缺乏行为反馈，并产生噪声搜索空间。研究强调，将LLM天真集成到搜索式APR中存在根本局限性，并建议采用混合方法。
正文节选
Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models Abstract Search-based Automated Program Repair (APR) techniques rely on carefully designed mutation operators to explore the space of candidate fixes. Recent advances in Large Language Models (LLMs) suggest that generative models could replace such operators by dynamically proposing repairs. In this paper, we investigate this hypothesis in the context of Cyber-Physical Syst