Lost in Code Generation: Reimagining the Role of Software Models in AI-driven Software Engineering

TL;DR

This paper advocates for reimagining software models as post-hoc tools to improve understanding, safety, and maintainability of AI-generated code, addressing fragility issues in rapid AI-driven software development.

Contribution

It introduces the concept of recovering and utilizing software models after code generation to enhance robustness and long-term system evolution.

Findings

Models can be recovered from AI-generated code to improve comprehension.

Using models post-hoc exposes risks and guides refinement.

This approach supports sustainable AI-driven software engineering.

Abstract

Generative AI enables rapid ``vibe coding," where natural language prompts yield working software systems. While this lowers barriers to software creation, it also collapses the boundary between prototypes and engineered software, leading to fragile systems that lack robustness, security, and maintainability. We argue that this shift motivates a reimagining of software models. Rather than serving only as upfront blueprints, models can be recovered post-hoc from AI-generated code to restore comprehension, expose risks, and guide refinement. In this role, models serve as mediators between human intent, AI generation, and long-term system evolution, providing a path toward sustainable AI-driven software engineering.