PROFES 2024
Mon 2 - Wed 4 December 2024 Tartu, Estonia

This program is tentative and subject to change.

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 conducted on a real-world project show that GPT-3.5 handled complex user stories well, achieving higher semantic similarity scores and ranking them, while GPT-4o performed consistently in prioritizing requirements. These early results show that LLMs perform tasks such as automating certain requirements analysis, particularly generating and prioritizing user stories.

This program is tentative and subject to change.

Tue 3 Dec

Displayed time zone: Athens change

14:00 - 15:30
PROFES Session 3: AI-Driven Approaches for Requirements EngineeringShort Papers and Posters / Research Papers / Industry Papers at UT Library - Room 2
14:00
18m
Research paper
Can Large Language Models (LLMs) compete with Human Requirement Reviewers? - Replication of an Inspection Experiment on Requirements Documents
Research Papers
Daniel Seifert Fraunhofer IESE, Lisa Jöckel Fraunhofer, Adam Trendowicz , Marcus Ciolkowski QAware, Thorsten Honroth , Andreas Jedlitschka Fraunhofer IESE
14:18
18m
Industry talk
AI Act High-Risk Requirements Readiness: Industrial Perspectives and Case Company Insights
Industry Papers
Matthias Wagner Lund University, Rushali Gupta Lund University, Markus Borg CodeScene, Emelie Engstrom Lund University, Michal Lysek Independent Researcher
14:36
12m
Short-paper
Early Results of an AI Multiagent System for Requirements Elicitation and Analysis
Short Papers and Posters
Malik Sami Tampere University, Muhammad Waseem University of Jyväskylä, Jyväskylä, Finland, Zheying Zhang Tampere University, Zeeshan Rasheed Tampere University, Kari Systa Tampere University, Pekka Abrahamsson Tampere University
14:48
12m
Short-paper
ReqGenie: GPT-Powered Conversational-AI for Requirements Elicitation
Short Papers and Posters
Farnaz Fotrousi Chalmers University of Technology and University of Gothenburg, Theocharis Tavantzis Chalmers and University of Gothenburg
15:00
30m
Talk
Session 3 Discussion
Research Papers