AI models that make CAD designs used to learn mostly from simple “draw-then-extrude” examples, so they struggled with real, complex parts.
AI programs called LLMs can now help write the tiny, super-fast pieces of code (kernels) that make GPUs run AI models efficiently.
The paper introduces Controlled Self-Evolution (CSE), a smarter way for AI to write and improve code quickly under a tight budget of tries.
This survey explains how AI agents remember things and organizes the whole topic into three clear parts: forms, functions, and dynamics.