Automated User Story Generation with Test Case Specification Using Large Language Model
Tajmilur Rahman, Yuecai Zhu
TL;DR
This work tackles the automation of Requirements Engineering by generating unit user stories and test specifications from high-level requirements using GeneUS, a GPT-4–based tool. It introduces Refine and Thought (RaT) prompting, a refinement-enhanced variant of Chain-of-Thought prompting, to reduce input noise and hallucinations in long, complex RE documents. The methodology yields JSON-formatted deliverables suitable for downstream integration with project management tools, and a RUST survey with 50 developers indicates the approach is broadly acceptable while highlighting improvements needed in specifiability and technical details. The findings suggest that RaT-enabled GenUS can reduce manual effort in the RE phase and potentially enable AutoAgile workflows, with future work extending data sources, knowledge embedding, and broader validation.
Abstract
Modern Software Engineering era is moving fast with the assistance of artificial intelligence (AI), especially Large Language Models (LLM). Researchers have already started automating many parts of the software development workflow. Requirements Engineering (RE) is a crucial phase that begins the software development cycle through multiple discussions on a proposed scope of work documented in different forms. RE phase ends with a list of user-stories for each unit task identified through discussions and usually these are created and tracked on a project management tool such as Jira, AzurDev etc. In this research we developed a tool "GeneUS" using GPT-4.0 to automatically create user stories from requirements document which is the outcome of the RE phase. The output is provided in JSON format leaving the possibilities open for downstream integration to the popular project management tools. Analyzing requirements documents takes significant effort and multiple meetings with stakeholders. We believe, automating this process will certainly reduce additional load off the software engineers, and increase the productivity since they will be able to utilize their time on other prioritized tasks.