The increasing demand for software development has driven interest in automating software engineering (SE) tasks using Large Language Models (LLMs). Recent efforts extend LLMs into multi-agent systems (MAS) that emulate collaborative development workflows, but these systems often fail due to three core deficiencies: under-specification, coordination misalignment, and inappropriate verification, arising from the absence of foundational SE structuring principles. This paper introduces Software Engineering Multi-Agent Protocol (SEMAP), a protocol-layer methodology that instantiates three core SE design principles for multi-agent LLMs: (1) explicit behavioral contract modeling, (2) structured messaging, and (3) lifecycle-guided execution with verification, and is implemented atop Google's Agent-to-Agent (A2A) infrastructure. Empirical evaluation using the Multi-Agent System Failure Taxonomy (MAST) framework demonstrates that SEMAP effectively reduces failures across different SE tasks. In code development, it achieves up to a 69.6% reduction in total failures for function-level development and 56.7% for deployment-level development. For vulnerability detection, SEMAP reduces failure counts by up to 47.4% on Python tasks and 28.2% on C/C++ tasks.

翻译：日益增长的软件开发需求推动了利用大语言模型（LLMs）自动化软件工程（SE）任务的兴趣。近期研究将LLMs扩展至模拟协作开发工作流的多智能体系统（MAS），但这些系统常因三个核心缺陷而失败：规范不足、协调失准和验证不当，这些缺陷源于缺乏基础的软件工程结构化原则。本文提出软件工程多智能体协议（SEMAP），这是一种协议层方法，为多智能体LLMs实例化了三项核心软件工程设计原则：（1）显式的行为契约建模，（2）结构化消息传递，以及（3）带验证的生命周期引导执行，并在谷歌的Agent-to-Agent（A2A）基础设施上实现。使用多智能体系统故障分类法（MAST）框架进行的实证评估表明，SEMAP能有效减少不同软件工程任务中的故障。在代码开发中，它在函数级开发上实现了高达69.6%的总故障减少，在部署级开发上实现了56.7%的减少。对于漏洞检测，SEMAP在Python任务上最多减少了47.4%的故障数量，在C/C++任务上减少了28.2%。