Multivocal Literature Reviews in Emergent Research Areas: An Experience Report
This paper was presented at the 3rd International Workshop on Methodological Issues with Empirical Studies in Software Engineering (WSESE 2026), co-located with ICSE 2026, in April 2026. In this experience report, we reflect on the process of conducting a Multivocal Literature Review (MLR) on the use of Generative Artificial Intelligence agents or multi-agent systems in the context of project management within Agile software development.
We examine the challenge of balancing timeliness with evidence maturity when analyzing a rapidly evolving field characterized by preprints and grey literature. We outline our research protocol, key design choices, challenges faced, and strategies for maintaining rigor alongside agility.
Our main contribution is a set of practical lessons on ensuring construct stability, handling preprints, dual-track quality assurance, and adjustment of the process to allow an iterative approach. These insights aim to assist researchers planning secondary studies in similarly dynamic research areas.