cs.SENov 11, 2025

Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale

Authors: Yangxiao Cai, Ruiyin Li, Peng Liang, Mojtaba Shahin, Zengyang Li, Aldeida Aleti, Chenxing Zhong

Organizations: School of Computer Science, Wuhan University, China · School of Computing Technologies, RMIT University, Australia · School of Computer Science, Central China Normal University, China

Abstract

As the complexity of Software Engineering (SE) tasks continues to escalate, Multi-Agent Systems (MASs) have emerged as a focal point of research and practice due to their autonomy and scalability. Furthermore, through leveraging the reasoning and planning capabilities of Large Language Models (LLMs), the application of LLM-based MASs in the field of SE is garnering increasing attention. However, there is no dedicated study that systematically explores the design of LLM-based MASs, including the Quality Attributes (QAs) on which designers mainly focus, the design patterns used by designers, and the rationale guiding the design of LLM-based MASs for SE tasks. To this end, we conducted a study to identify the QAs that LLM-based MASs for SE tasks focus on, the design patterns used in the MASs, and the design rationale for the MASs. We collected 106 papers on LLM-based MASs for SE tasks as the source. Our study shows that: (1) Code Generation is the most common SE task solved by LLM-based MASs among ten identified SE tasks, (2) Functional Suitability is the QA on which designers of LLM-based MASs pay the most attention, (3) Role-Based Cooperation is the design pattern most frequently employed among 16 patterns used to construct LLM-based MASs, and (4) Improving the Quality of Generated Code is the most common rationale behind the design of LLM-based MASs. Building on the study results, we presented the implications for the design of LLM-based MASs to support SE tasks.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows

    Oct 2, 2026Merve Astekin, Yan Naing Tun, Arda Goknil +5Software Engineering AgentsLLM Agent Evaluation

  2. Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain

    Mar 10, 2026Yen-Ku Liu, Yun-Cheng TsaiAI-Assisted Software DevelopmentSoftware Engineering

  3. Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis

    Jul 30, 2026Linus Sander, Fengjunjie Pan, Vahid Zolfaghari +3Multi-Agent LLM SystemsMulti-Agent System Optimization