Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study
For domain experts without programming skills using vibe coding in runtime-adaptive systems, this work demonstrates that precise automated feedback can replace human code inspection, addressing a key reliability bottleneck.
The paper investigates feedback-based automated verification for LLM-generated code in Collective Adaptive Systems, showing that fine-grained constraint violations enable reliable adaptation managers within a few iterations, while coarse feedback stalls, suggesting feedback precision can eliminate the need for human code inspection.
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.