Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914091382079488 |
|---|---|
| author | Mao, Zhenyu Keung, Jacky Zhang, Fengji Liu, Shuo Wang, Yifei Li, Jialong |
| author_facet | Mao, Zhenyu Keung, Jacky Zhang, Fengji Liu, Shuo Wang, Yifei Li, Jialong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12120 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach Mao, Zhenyu Keung, Jacky Zhang, Fengji Liu, Shuo Wang, Yifei Li, Jialong Software Engineering 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. |
| title | Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2510.12120 |