Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study

TL;DR

This study explores feedback-based automated verification of LLM-generated adaptation managers in Collective Adaptive Systems, emphasizing the importance of precise feedback for reliable, human-inspection-free code refinement.

Contribution

It introduces a novel verification approach combining architectural and functional constraints with a new logic, FCL, demonstrating effective feedback for code correctness without human inspection.

Findings

Fine-grained constraint violations enable quick correction of adaptation managers.

Simple feedback often stalls, highlighting the importance of feedback precision.

Feedback precision is crucial for reliable vibe coding in expert-designed systems.

Abstract

Vibe coding inherently assumes iterative refinement of LLM-generated code through feedback loops. While effective for conventional software tasks, its reliability in runtime-adaptive systems is unclear -- especially when generated code is not manually inspected. This paper studies feedback-based automated verification of LLM-generated adaptation managers in Collective Adaptive Systems (CAS). We focus on the key challenges of verification in the loop: how to detect failures of generated code at runtime and how to report them precisely enough for an LLM to fix them. We combine the adaptation loop with a vibe-coding feedback loop where correctness is checked against (i) generic architectural constraints and (ii) functional constraints formalized in Functional Constraints Logic (FCL), a novel first-order temporal logic over potentially finite traces. Conducting the Dragon Hunt CAS case study, we show that fine-grained constraint violations provide actionable feedback that typically yields a valid adaptation manager within a few iterations, while simple coarse metric-based feedback often stalls. Our findings suggest that feedback precision is the dominant factor for reliable vibe coding in systems designed by domain experts with no programming skills, thereby obviating the need for human code inspection.