A4 Article in conference proceedings
Early Results of an AI Multiagent System for Requirements Elicitation and Analysis (2025)

Sami, M. A., Waseem, M., Zhang, Z., Rasheed, Z., Systä, K., & Abrahamsson, P. (2025). Early Results of an AI Multiagent System for Requirements Elicitation and Analysis. In D. Pfahl, J. G. Huerta, J. Klünder, & H. Anwar (Eds.), Product-Focused Software Process Improvement : 25th International Conference, PROFES 2024, Tartu, Estonia, December 2–4, 2024, Proceedings (pp. 307-316). Springer. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-031-78386-9_20

JYU authors or editors

Publication details

All authors or editors: Sami, Malik Abdul; Waseem, Muhammad; Zhang, Zheying; Rasheed, Zeeshan; Systä, Kari; Abrahamsson, Pekka

Parent publication: Product-Focused Software Process Improvement : 25th International Conference, PROFES 2024, Tartu, Estonia, December 2–4, 2024, Proceedings

Parent publication editors: Pfahl, Dietmar; Huerta, Javier Gonzalez; Klünder, Jil; Anwar, Hina

Place and date of conference: Tartu, Estonia, 2.-4.12.2024

ISBN: 978-3-031-78385-2

eISBN: 978-3-031-78386-9

Journal or series: Lecture Notes in Computer Science

ISSN: 0302-9743

eISSN: 1611-3349

Publication year: 2025

Publication date: 27/11/2024

Pages range: 307-316

Number of pages in the book: 416

Publisher: Springer

Place of Publication: Cham

Publication country: Switzerland

Publication language: English

DOI: https://doi.org/10.1007/978-3-031-78386-9_20

Publication open access: Not open

Publication channel open access: 

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/99060

Abstract

In agile software development, user stories capture requirements from the user’s perspective, emphasizing their needs and each feature’s value. Writing concise and quality user stories is necessary for guiding software development. Alongside user story generation, prioritizing these requirements ensures that the most important features are developed first, maximizing project value. This study explores the use of Large Language Models (LLMs) to automate the process of user story generation, quality assessment, and prioritization. We implemented a multi-agent system using Generative Pre-trained Transformers (GPT), specifically GPT-3.5 and GPT-4o, to generate and prioritize user stories from the initial project description. Our experiments on a real-world project demonstrate that GPT-3.5 handled user story generation well, achieving a higher semantic similarity score comnpared to the GPT-4o. Both models showed consistent performance in prioritizing requirements, effectively identifying the core features of the application. These early results indicate that LLMs have significant potential for automating requirements analysis, particularly generating and prioritizing user stories.

Keywords: artificial intelligence; agile methods; software design; software development

Contributing organizations

Ministry reporting: Yes

VIRTA submission year: 2025

Preliminary JUFO rating: 1