Logo image
Back
Better Together: An LLM-assisted approach to designing software architectures using Attribute-Driven Design
Journal article   Peer reviewed

Better Together: An LLM-assisted approach to designing software architectures using Attribute-Driven Design

Humberto Cervantes, Rick Kazman and Yuanfang Cai
IEEE transactions on software engineering, pp 1-17
22 Jun 2026
DOI: https://doi.org/10.1109/TSE.2026.3706446

Abstract

Amplitude shift keying Codes Design methodology Large Language Model Large language models Modeling Planning Reviews Software architecture Software design Architecture Computer Architecture
Designing effective software architectures is a complex, iterative process that traditionally relies on expert judgment. This paper proposes an approach for Large Language Model (LLM)-assisted software architecture design leveraging the Attribute-Driven Design (ADD) method. By providing an LLM with an explicit description of ADD and an architect persona, our method guides the LLM to collaboratively produce a structured iteration plan and a detailed architecture design document. We have validated this approach in two ways: through the comparison of an LLM-generated solution with a proven solution, and through the evaluation of an LLM-generated architecture by a team of four professional architects. We also compare designs produced with and without our ADD-guided approach. Our results show that our LLM-assisted ADD process produces thorough architecture documentation and that the LLM-generated architectures satisfy architectural drivers. We also argue that human feedback and guidance are still needed in the design process, particularly with respect to the most critical and nuanced design decisions.

Metrics

1 Record Views

Details

Logo image