AI RESEARCH
Using LLMs in Software Design: An Empirical Study of GitHub and A Practitioner Survey
arXiv CS.AI
•
ArXi:2605.01392v1 Announce Type: cross Recent advancements in Large Language Models (LLMs) have nstrated significant potential across a wide range of software engineering tasks, including software design, an area traditionally regarded as highly dependent on human expertise and judgment. However, there has been little research focusing on how LLMs are used in software design, nor on the associated benefits and drawbacks. This paper aims to bridge this gap by empirically investigating how software developers utilize LLMs in the context of software design.