LLM-Based Agents for Automating the Enhancement of User Story Quality: An Early Report
Zheying Zhang, Maruf Rayhan, Tomas Herda, Manuel Goisauf, Pekka Abrahamsson
Abstract
Abstract In agile software development, maintaining high-quality user stories is crucial, but also challenging. This study explores the application of large language models (LLMs) to improve the quality of user stories within the agile teams of Austrian Post Group IT. We developed an Autonomous LLM-based Agent System (ALAS) and evaluated its impact on user story quality with 11 participants from six agile teams. Our findings reveal the potential of LLMs in improving user story quality, provide a practical example, and lay the foundation for future research into the broad application of LLMs in a variety of industry settings.
Topics & Concepts
Agile software developmentUser storyQuality (philosophy)Variety (cybernetics)Computer scienceEngineeringKnowledge managementEngineering managementSoftwareSoftware engineeringSoftware developmentArtificial intelligenceEpistemologyProgramming languagePhilosophySoftware Engineering Techniques and PracticesSoftware Engineering ResearchOpen Source Software Innovations