An LLM-assisted approach to designing software architectures using ADD

2025-06-27

AI Summary

This work addresses the problem of software architecture design’s overreliance on expert knowledge and high iteration costs. We propose an LLM-augmented framework grounded in Attribute-Driven Design (ADD), which explicitly encodes the ADD methodology into structured prompts and incorporates architect role specification alongside multi-turn iterative reasoning to enable human-AI co-creation of traceable and reproducible architectural artifacts. Our key contributions are: (1) the first systematic integration of the ADD process into LLM prompt engineering, and (2) role-guided prompting to enhance domain expertise and output consistency. Empirical evaluation on industrial case studies demonstrates that the generated architectures align closely with industry-grade solutions across critical quality attributes (e.g., performance, modifiability, security). Expert assessment validates the framework’s effectiveness and identifies concrete avenues for refinement, including improved constraint handling and cross-layer consistency enforcement.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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.

Problem

• LLM-assisted software architecture design using ADD method
• Reducing reliance on expert judgment in architecture design
• Validating LLM-generated designs against professional standards

Innovation

• LLM-assisted ADD method for architecture design
• Structured iteration plan with architect persona
• Human oversight in iterative refinement process