Spherocentric Memory Theory — Symbolic AI for Critical Autonomy

This work proposes and demonstrates the Spherocentric Memory Theory as an innovative approach to symbolic agents with autonomous decision-making. Through modeling interconnected cognitive spheres and applying activation vectors with persistent memory and symbolic feedback, it presents a functional decision-making architecture that does not rely on conventional statistical learning. The results are based on real simulations and interactive visualizations using Python, C++, WebGL, and a modular symbolic agent.