Reproduce “Aether: Network Validation Using Agentic AI and Digital Twin” 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

Jordan Auge, Sam Betts, Giovanna Carofiglio, Giulio Grassi, Martin Gysi, John Kenneth d'Souza

Aether checks proposed network changes by having AI agents translate an operator’s intent into tailored tests, which a structured digital twin runs on candidate network snapshots. In an eight-scenario synthetic benchmark, it detected 94% of faulty candidates. In two past ISP incidents replayed on a laboratory replica, it rejected both faulty candidates, with less than complete average per-run test coverage.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.