An autonomous AI system is now writing and deploying its own Linux kernel code to improve Wi-Fi speeds better than human engineers.
Networking engineering is a slow process of manual testing and code writing. This IteRate system automates the entire cycle by formulating hypotheses and writing eBPF code to control Wi-Fi hardware. It then tests the code in real-time, learns from the results, and iterates on the design. In many tests, it outperformed industry standards that have been in place for a decade. This proves that the most hardcore levels of software engineering can now be handled by autonomous research loops.
IteRate: Autonomous AI Synthesis of In-Kernel eBPF Wi-Fi Rate Control Algorithms
arXiv · 2605.02542
Wi-Fi rate adaptation remains a persistent challenge in wireless networking. Deployed algorithms like Minstrel-HT have remained largely stagnant for over a decade, relying on hand-tuned heuristics that fail to generalize to the complexity of modern wireless environments. We present \name, an autonomous research system that closes the loop on rate control development. IteRate uses a multi-agent AI architecture to conduct the full scientific cycle: formulating hypotheses, writing eBPF programs tha