The Software Engineering Simulations Lab: Agentic AI for RE Quality Simulations
This work addresses the problem of costly and scarce empirical data on requirements quality for software engineering researchers, though it is incremental as it introduces a new simulation tool rather than a breakthrough.
The paper tackles the lack of empirical evidence on how requirement defects affect downstream activities by proposing agentic AI simulations to replicate software engineering processes, with a feasibility study showing that even a naive implementation yields executable simulations.
Context and motivation. Requirements Engineering (RE) quality still lacks empirical evidence on how specific requirement defects affect downstream activities. Problem: However, empirical data on the detailed effects of requirements quality defects is scarce, since it is costly to obtain. Furthermore, with the advent of AI-based development, the requirements quality factors may change: Requirements are no longer only consumed by humans, but increasingly also by AI agents, which might lead to a different efficient and effective requirements style. Principal ideas: We propose to extend the RE research toolbox with Agentic AI simulations, in which software engineering (SE) processes are replicated by standardized agents in qualitative simulations. We argue that their speed and simplicity makes them a valuable addition to RE research, although limitations in replicating human behavior need to be studied and understood. Contribution: This paper contributes a first concept, a research roadmap, a prototype, and a first feasibility study for RE simulations with agentic AI. Study results indicate that even a naïve implementation leads to executable simulations, encouraging technical improvements along with broader application in RE research.