Collaborative and AI-Supported Requirements Elicitation: An Empirical Study

2026-06-22

AI Summary

This study investigates how to effectively integrate artificial intelligence with stakeholder collaboration to enhance the quality and efficiency of requirements elicitation. Through a mixed-methods controlled experiment, four approaches were compared: traditional collaborative elicitation, direct generation by large language models (LLMs), LLM-based generation from discussion transcripts, and a novel hybrid method that synthesizes stakeholder collaboration with LLM augmentation. The results demonstrate that the hybrid approach is the first to empirically yield significantly higher-quality requirements artifacts—producing documentation that is clearer, more actionable, and better aligned with user needs—while also improving participants’ experience of the elicitation process. These findings underscore the unique value of human-AI collaboration in requirements engineering, outperforming both purely manual and purely AI-driven methods.

Abstract

Requirements elicitation requires stakeholders to communicate needs, negotiate priorities, and collaboratively construct knowledge that can be transformed into software requirements artifacts. Recent advances in LLMs have created opportunities to support these activities through AI-assisted collaboration and automated artifact generation. However, limited empirical evidence is available regarding how AI-supported collaborative environments influence requirements elicitation outcomes. In this study, we conducted a mixed-method controlled experiment comparing four requirements elicitation approaches: collaborative elicitation without AI support, collaborative elicitation supported by the Strateegia platform and its GPT-powered Writer applet, direct requirements generation using a Large Language Model, and requirements generation from collaborative discussion transcripts using a Large Language Model. We evaluated the resulting artifacts using quality criteria derived from ISO/IEC/IEEE 29148 and collected participant perceptions regarding the elicitation process. Our findings indicate that approaches combining stakeholder collaboration and AI-supported synthesis produced the highest-rated requirements artifacts and were perceived as clearer and easier to execute than traditional collaborative elicitation. The results suggest that generative AI can support the transformation of collaboratively generated knowledge into structured requirements documentation while preserving the value of stakeholder participation. We discuss implications for AI-supported requirements elicitation and human-AI collaboration in Requirements Engineering.

Problem

• requirements elicitation
• AI-supported collaboration
• Large Language Models
• empirical study
• human-AI collaboration

Innovation

• AI-supported collaboration
• requirements elicitation
• Large Language Models
• human-AI collaboration
• empirical study