IteRate: Autonomous AI Synthesis of In-Kernel eBPF Wi-Fi Rate Control Algorithms

2026-05-04

AI Summary

This work addresses the limitations of traditional Wi-Fi rate control algorithms, which rely on hand-tuned heuristics and struggle to adapt to complex, dynamic wireless environments. The authors present the first AI-driven, closed-loop rate control research and development system, featuring a structured multi-agent architecture that automates hypothesis generation, eBPF kernel program synthesis, deployment, and telemetry collection, alongside an end-to-end automated evaluation pipeline. Key innovations include a kernel-level per-frame telemetry interface, a hypothesis-driven multi-agent collaboration mechanism, and an embedded auto-deployment framework. Evaluated on a 58-node real-world testbed, the system achieves a 21% improvement in web page load time, a 7% gain in video quality of experience (QoE), and a 21% increase in peak throughput compared to Minstrel.

Abstract

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 that run inside the Linux kernel, deploying them over-the-air to Wi-Fi devices, collecting fine-grained telemetry for analysis, and iterating based on experimental evidence, all without human intervention. IteRate makes three contributions. (1) a novel kernel module that exposes per-frame hardware telemetry including modulation and coding schemes (MCS) and retry counts to eBPF programs, (2) a structured agentic AI architecture employing specialized agents for algorithm design, experiment execution, and data analysis, coordinated via a hypothesis-driven research protocol with persistent knowledge, and (3) a closed-loop pipeline that automates the cross-compilation, deployment, and evaluation of in-kernel logic onto embedded Wi-Fi targets. On a 58-node testbed running five workloads. relative to the well-known Minstrel algorithm, IteRate achieves 21% faster web-page loads, 7% higher video quality of experience (QoE), and 21% higher peak throughput. Our work demonstrates that AI agents, when equipped with appropriate kernel-level hooks and a disciplined scientific workflow, can effectively automate the research required to design Wi-Fi rate controllers.

Problem

• Wi-Fi rate control
• rate adaptation
• wireless networking
• eBPF
• autonomous AI

Innovation

• eBPF
• Wi-Fi rate control
• autonomous AI agents
• in-kernel telemetry
• closed-loop research automation