Toward Reproducing Network Research Results Using Large Language Models

Reproducing research results is important for the networking community. The current best practice typically resorts to: (1) looking for publicly available prototypes; (2) contacting the authors to get a private prototype; or (3) manually implementing a prototype following the description of the publication. However, most published network research does not have public prototypes and private ones are hard to get. As such, most reproducing efforts are spent on manual implementation based on the publications, which is both time and labor consuming and error-prone. In this paper, we boldly propose reproducing network research results using the emerging large language models (LLMs). We first prove its feasibility with a small-scale experiment, in which four students with essential networking knowledge each reproduces a different networking system published in prominent conferences and journals by prompt engineering ChatGPT. We report our observations and lessons and discuss future open research questions of this proposal.