14 papers
Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models
Ayesha Irshad, Pablo Valle, Jon Ayerdi +1
Search-based Automated Program Repair (APR) techniques rely on carefully designed mutation operators to explore the space of candidate fixes. Recent advances in Large Language Mode…
Delta Debugging for Cyber-Physical Systems with Flaky Test Executions
Pablo Valle, Shaukat Ali, Aitor Arrieta
The paper introduces three delta debugging algorithms that use statistical analysis and repeated executions to isolate minimal failure-inducing inputs for stochastic cyber‑physical…
Foundation Models for Software Engineering of Cyber-Physical Systems: the Road Ahead
Chengjie Lu, Pablo Valle, Jiahui Wu +4
Foundation Models (FMs), particularly Large Language Models (LLMs), are increasingly used to support various software engineering activities (e.g., coding and testing). Their adopt…
MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models
Pablo Valle, Shaukat Ali, Aitor Arrieta +1
Vision-Language-Action (VLA) models are emerging robotic control systems that integrate perception, language understanding, and action generation in a unified architecture. Existin…
FATE-VLA:Failue-aware test generation for vision-language-action models
Arusa Kanwal, Pablo Valle, Shaukat Ali +1
Vision-Language-Action (VLA) models are increasingly used as generalist robot policies, yet their evaluation still relies largely on static benchmarks that randomly sample task sce…
VISOR: A Vision-Language Model-based Test Oracle for Testing Robots
Prasun Saurabh, Pablo Valle, Aitor Arrieta +2
Testing robots requires assessing whether they perform their intended tasks correctly, dependably, and with high quality, a challenge known as the test oracle problem in software t…