Reproduce “Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xi Zheng, Ivan Ruchkin, Hong Jin Kang, Tevfik Bultan, Vijay Ganesh, Taylor T. Johnson, Ziyang Li, Lei Ma and 6 more
The authors propose an assurance architecture for learning-enabled cyber-physical systems, making models, interfaces, and contracts explicit. Foundation models assist perception, reasoning, and planning; testing checks system behavior against requirements, while formal verification checks tractable properties. A Simplex runtime layer can constrain actions or switch controllers. The paper presents a research agenda, not an evaluated system or demonstrated safety improvement.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.