Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development
The paper introduces Agentic Agile-V, a framework aimed at improving software and hardware development processes through agentic AI coding systems. It highlights that while these systems can enhance productivity in certain tasks, they do not automatically guarantee better engineering outcomes. The author emphasizes the importance of maintaining engineering discipline and the value of structured requirements and verification processes.
- ▪Agentic AI coding systems can perform various tasks such as inspecting repositories and running tests.
- ▪Current studies show mixed results regarding the productivity gains from autonomous code generation.
- ▪The paper proposes a new process framework called Agentic Agile-V to improve engineering outcomes.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Software Engineering arXiv:2605.20456 (cs) [Submitted on 19 May 2026] Title:Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development Authors:Christopher Koch View a PDF of the paper titled Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development, by Christopher Koch View PDF HTML (experimental) Abstract:Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current evidence does not support the simple claim that autonomous code generation automatically improves engineering outcomes.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
