{"ID":2855533,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12120","arxiv_id":"2510.12120","title":"Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach","abstract":"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.","short_abstract":"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: un...","url_abs":"https://arxiv.org/abs/2510.12120","url_pdf":"https://arxiv.org/pdf/2510.12120v1","authors":"[\"Zhenyu Mao\",\"Jacky Keung\",\"Fengji Zhang\",\"Shuo Liu\",\"Yifei Wang\",\"Jialong Li\"]","published":"2025-10-14T03:49:30Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}