LLM-based systems used for tutoring can produce fluent and apparently plausible explanations, but they do not guarantee Technical Correctness, which is paramount in STEM fields such as Electrical Circuit Analysis. This study investigates how three LLM-based response systems—parametric model knowledge (Pure LLM), Retrie...
André Rocha, João Ferreira, Paulo C. Oliveira et al.· Computers· 0 citations
This paper’s key contribution is a module extension for an existing ROS-focused container framework that leverages Kubernetes’ capabilities—controlled rolling updates, ROS-adapted readiness checks, distributed workload management, and embedded observability—to bridge cloud-native practices with robotics development.
Nicholas Hopf, Rafael Arrais, Pedro Melo et al.· Applied Sciences· 0 citations
The results show that the proposed RAG agent substantially improves the lightweight base model and produces transparent, syllabus-grounded answers that experts rated as correct and concise, while GPT-4.5 retains an edge on longer, multistep, and topology-intensive tasks.
André Rocha, Paulo C. Oliveira, João Ferreira et al.· Applied Sciences· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
