Paper Examines LLM Agents for Software Architecture
Semantic ScholarFriday, November 6, 2026
- •IEEE Software paper examines LLM-powered agents for microservice architecture design
- •Authors include Marco Calamo, Flavia Monti and F. Spaziani
- •AI assistants generate code snippets but lack a holistic view of module interactions
A paper by Marco Calamo, Flavia Monti, F. Spaziani and coauthors, published in IEEE Software in 2026, examines the use of large language model-powered agents to design and improve microservice-based software.
Large language models have rapidly changed how developers write and test code, but their use in software architecture design remains limited. Current AI assistants can generate useful code snippets yet lack a holistic view of how modules should interact to form reliable systems.