Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper investigates the feasibility of "vibe-coding," an iterative LLM-based code refinement process driven by automated feedback, for runtime-adaptive systems. They address the challenges of detecting and reporting failures in LLM-generated adaptation managers within Collective Adaptive Systems (CAS). By using Functional Constraints Logic (FCL), a novel first-order temporal logic, to formalize functional and architectural constraints, they demonstrate that fine-grained constraint violation feedback enables LLMs to generate valid adaptation managers within a few iterations, eliminating the need for human code inspection.
Forget manual code reviews: precise, automated feedback on constraint violations lets LLMs iteratively refine code for runtime-adaptive systems, achieving validity without human intervention.
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.