Composable OS Kernel Architectures for Autonomous Intelligence
This addresses the need for adaptive OS kernels in edge devices, cloud infrastructure, and embedded real-time environments, representing a new paradigm rather than an incremental improvement.
The research tackled the problem of operating systems being static resource managers by proposing a new OS kernel architecture that integrates AI into kernels, enabling them to adapt to autonomous intelligent applications through AI-native environments and neurosymbolic designs.
As intelligent systems permeate edge devices, cloud infrastructure, and embedded real-time environments, this research proposes a new OS kernel architecture for intelligent systems, transforming kernels from static resource managers to adaptive, AI-integrated platforms. Key contributions include: (1) treating Loadable Kernel Modules (LKMs) as AI-oriented computation units for fast sensory and cognitive processing in kernel space; (2) expanding the Linux kernel into an AI-native environment with built-in deep learning inference, floating-point acceleration, and real-time adaptive scheduling for efficient ML workloads; and (3) introducing a Neurosymbolic kernel design leveraging Category Theory and Homotopy Type Theory to unify symbolic reasoning and differentiable logic within OS internals. Together, these approaches enable operating systems to proactively anticipate and adapt to the cognitive needs of autonomous intelligent applications.