Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design
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.
Tue 24 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
10:30 - 12:30 | Architecture, Services, and CloudIndustry Papers / Demonstrations / Research Papers / Ideas, Visions and Reflections at Andromeda Chair(s): Paris Avgeriou University of Groningen, The Netherlands | ||
10:30 10mTalk | Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design Ideas, Visions and Reflections Yiran Zhang , Ruiyin Li Wuhan University, China; University of Groningen, The Netherlands, Peng Liang Wuhan University, China, Weisong Sun Nanyang Technological University, Yang Liu Nanyang Technological University | ||
10:40 10mTalk | Designing for Scalability: Building a Universal Serverless Messaging Architecture with Apache RocketMQ Industry Papers Juntao Ji Alibaba Cloud Computing Co. Ltd., Yubao Fu Alibaba Cloud Computing Co. Ltd., Rongtong Jin Alibaba Cloud Computing Co. Ltd., Qingshan Lin Alibaba Cloud Computing Co. Ltd. | ||
10:50 20mTalk | A Multimodal Intelligent Change Assessment Framework for Microservice Systems Based on Large Language Models Industry Papers Yongqian Sun Nankai University, zhengtinghua Nankai university, Xidao Wen BizSeer, Weihua Kuang Nankai university, Heng Liu CHINA TIANCHEN ENGINEERING CORPORATION LTD., Shenglin Zhang Nankai University, Chao Shen Nankai University, Bo Wu Tencent Technologies, Dan Pei Tsinghua University | ||
11:10 20mTalk | TracePicker: Optimization-based Trace Sampling for Microservice-based Systems Research Papers Shuaiyu Xie School of Computer Science, Wuhan University, China, Jian Wang Wuhan University, Maodong Li School of Computer Science, Wuhan University, China, Peiran Chen School of Computer Science, Wuhan University, China, Jifeng Xuan Wuhan University, Bing Li Wuhan University DOI | ||
11:30 10mTalk | Analyzing Evolution of Microservice-based Systems Demonstrations Tomas Cerny University of Arizona, Gabriel Goulis University of Arizona, Samanta Perry University of Arizona, Malia Edmonds University of Arizona, Amr Elsayed The University of Arizona, Matteo Esposito University of Oulu, Alexander Bakhtin University of Oulu, Valentina Lenarduzzi University of Oulu, Davide Taibi University of Oulu | ||
11:40 20mTalk | SemServGen: Advancing Industrial Domain-Specific Language Engineering through Semantic Service Generation Industry Papers Yong Wang Beihang University, Ning Ge School of Software, Beihang University, Jingyao Li Beihang University, Loulin Wang Beihang University, Guangyu Zhou Huawei, Chengrui Deng Huawei, Li Zhang Beihang University, Chunming Hu Beihang University | ||
12:00 10mTalk | CloudHeatMap: Heatmap-Based Monitoring for Large-Scale Cloud Systems Demonstrations Sarah Sohana Rogers Communications Canada Inc., Toronto, Canada, William Pourmajidi Toronto Metropolitan University, Toronto, Canada, John Steinbacher IBM, Andriy Miranskyy Toronto Metropolitan University (formerly Ryerson University) DOI Pre-print | ||
12:10 20mTalk | Te-PID: An Adaptive Erasure Coding Temperature Management System for Optimized Cloud Storage Industry Papers Pei Xiao Peking University, Lu Wang Microsoft Research, Fangkai Yang Microsoft Research, Guoqing Geng Microsoft, Haoran Li Microsoft, Jeff Zhu Microsoft, Yu Kang Microsoft Research, Yifan Li Microsoft, Terry Chen Microsoft, Yue Chen Microsoft, Saravan Rajmohan Microsoft 365, Qi Zhang Microsoft |
Andromeda is located close to the restaurant and the bar, at the end of the corridor on the side of the bar.
From the registration desk, go towards the restaurant, turn left towards the bar, walk until the end of the corridor.