Reproduce “Evolving Inspectable O-RAN Slicing xApps with LLMs” 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
Faezeh Dehghan Tarzjani, Bhaskar Krishnamachari
The authors use an LLM to evolve readable Python radio-slicing controllers offline, scoring candidates in a simulator before deploying the selected module unchanged in an O-RAN control path. During a deep fade on the POWDER 5G testbed, it raised best-effort throughput to 228.6 Mbps, 44.5% above the best static split; this result does not exceed PPO or generalize beyond this setup.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.