Beyond the Black Box: A Cognitive Architecture for Explainable and Aligned AI

TL;DR

This paper presents 'Weight-Calculatism,' a novel cognitive architecture that enhances explainability and value alignment in AI, aiming to advance toward trustworthy Artificial General Intelligence through atomic cognition and traceable decision-making.

Contribution

It introduces a first-principles-based architecture with atomic cognition and an interpretable weight-calculation model, enabling radical explainability and intrinsic alignment for AGI.

Findings

Achieves transparent, human-like reasoning in complex scenarios

Demonstrates robust learning and decision traceability

Provides a practical foundation for trustworthy AGI

Abstract

Current AI paradigms, as "architects of experience," face fundamental challenges in explainability and value alignment. This paper introduces "Weight-Calculatism," a novel cognitive architecture grounded in first principles, and demonstrates its potential as a viable pathway toward Artificial General Intelligence (AGI). The architecture deconstructs cognition into indivisible Logical Atoms and two fundamental operations: Pointing and Comparison. Decision-making is formalized through an interpretable Weight-Calculation model (Weight = Benefit * Probability), where all values are traceable to an auditable set of Initial Weights. This atomic decomposition enables radical explainability, intrinsic generality for novel situations, and traceable value alignment. We detail its implementation via a graph-algorithm-based computational engine and a global workspace workflow, supported by a preliminary code implementation and scenario validation. Results indicate that the architecture achieves transparent, human-like reasoning and robust learning in unprecedented scenarios, establishing a practical and theoretical foundation for building trustworthy and aligned AGI.