Vibe coding has emerged as a fashionable practice since early 2025, shifting developers’ attention from pure code production toward comprehensive capabilities, through collaboration with artificial intelligence (AI). Alongside such a trend, a related notion, vibe researching has appeared in gray literature, referring to a co-research approach of conducting research with AI. Although no empirical studies have examined this phenomenon, as it is a very new concept, an increasing number of software engineering (SE) researchers are utilizing AI in various research stages in increasingly diverse ways, far beyond the language enhancement roles typically acknowledged in recent papers’ AI declaration. It raises the need for up-to-date methodological guidance to mitigate AI hallucinations and remain academically rigorous and sustainable in SE research. In this position paper, we illustrate two empirical practices towards the vibe researching approach, discussing challenges from both junior and senior researchers’ perspectives, and proposing a framework for our SE community.

@inproceedings{paperbot12632,
  title = {Positioning Vibe Researching in Software Engineering: Dual Perspectives from Junior and Senior Researchers},
  author = {Nan Yang and Xiaofeng Wang and Sami Hyrynsalmi},
  booktitle = {ICSE},
  year = {2026},
  doi = {10.1145/3793657.3793896}
}