An LLM-assisted approach to designing software architectures using ADD

TL;DR

This paper introduces an LLM-assisted approach to software architecture design using the ADD method, enabling collaborative creation of architecture artifacts with validation through case studies and professional evaluation.

Contribution

It presents a novel method integrating LLMs with ADD for architecture design, demonstrating effective collaboration and validation with real-world case studies.

Findings

Generated architectures closely match proven solutions

LLM-assisted process partially satisfies architectural drivers

Highlights importance of human oversight in LLM-based design

Abstract

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 using the Attribute-Driven Design (ADD) method. By providing an LLM with an explicit description of ADD, an architect persona, and a structured iteration plan, our method guides the LLM to collaboratively produce architecture artifacts with a human architect. We validate the approach through case studies, comparing generated designs against proven solutions and evaluating them with professional architects. Results show that our LLM-assisted ADD process can generate architectures closely aligned with established solutions and partially satisfying architectural drivers, highlighting both the promise and current limitations of using LLMs in architecture design. Our findings emphasize the importance of human oversight and iterative refinement when leveraging LLMs in this domain.