3 papers
cs.SE2026
Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study
Michal Töpfer, František Plášil, Tomáš Bureš +1
Vibe coding inherently assumes iterative refinement of LLM-generated code through feedback loops. While effective for conventional software tasks, its reliability in runtime-adapti…
cs.AI2026
Feedback-based Automated Verification in Vibe Coding of CAS Adaptation Built on Constraint Logic
Michal Töpfer, František Plášil, Tomáš Bureš +1
In CAS adaptation, a challenge is to define the dynamic architecture of the system and changes in its behavior. Implementation-wise, this is projected into an adaptation mechanism,…
cs.SE2025
Towards Continuous Experiment-driven MLOps
Keerthiga Rajenthiram, Milad Abdullah, Ilias Gerostathopoulos +5
Despite advancements in MLOps and AutoML, ML development still remains challenging for data scientists. First, there is poor support for and limited control over optimizing and evo…