# Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design

arXiv: https://arxiv.org/abs/2503.20536 · HTML: https://mlsanity.com/paper/2503.20536/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 13 of 13)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation](https://mlsanity.com/paper/2405.02580/) (2024)
- [Investigating and Designing for Trust in AI-powered Code Generation Tools](https://mlsanity.com/paper/2305.11248/) (2023)
- [Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study](https://mlsanity.com/paper/2403.01709/) (2024)
- [ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization](https://mlsanity.com/paper/2407.01646/) (2024)
- [Software Architecture Recovery with Information Fusion](https://mlsanity.com/paper/2311.04643/) (2023)
- [Eliminating Backdoors in Neural Code Models for Secure Code Understanding](https://mlsanity.com/paper/2408.04683/) (2024)
- [Demonstration Attack against In-Context Learning for Code Intelligence](https://mlsanity.com/paper/2410.02841/) (2024)
- [Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization](https://mlsanity.com/paper/2503.10737/) (2025)

## Built on by (most cited first, 7 of 7)

- [BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents](https://mlsanity.com/paper/2601.04566/) (2026)
- [Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision](https://mlsanity.com/paper/2508.18675/) (2025)
- [A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards](https://mlsanity.com/paper/2505.13766/) (2025)
- [MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration](https://mlsanity.com/paper/2507.21382/) (2025)
- [A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AI](https://mlsanity.com/paper/2510.26275/) (2025)
- [Can AI Agents Generate Microservices? How Far are We?](https://mlsanity.com/paper/2603.09004/) (2026)
- [Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory](https://mlsanity.com/paper/2606.01385/) (2026)

## Abstract (arXiv)

Architecture design is a critical step in software development. However, creating a high-quality architecture is often costly due to the significant need for human expertise and manual effort. Recently, agents built upon Large Language Models (LLMs) have achieved remarkable success in various software engineering tasks. Despite this progress, the use of agents to automate the architecture design process remains largely unexplored. To address this gap, we envision a Knowledge-based Multi-Agent Architecture Design (MAAD) framework. MAAD uses agents to simulate human roles in the traditional software architecture design process, thereby automating the design process. To empower these agents, MAAD incorporates knowledge extracted from three key sources: 1) existing system designs, 2) authoritative literature, and 3) architecture experts. By envisioning the MAAD framework, we aim to advance the full automation of application-level system development.