A Coherence-Based Measure of AGI

TL;DR

This paper proposes a new coherence-based measure for evaluating AGI that emphasizes balanced capabilities across domains, addressing limitations of traditional averaging methods by penalizing imbalances and revealing bottlenecks.

Contribution

It introduces a novel AUC-based metric integrating multiple compensability regimes, providing a more rigorous and interpretable assessment of AGI coherence and progress.

Findings

The coherence-based measure highlights imbalances in cognitive profiles.

Application to CHC model demonstrates detection of performance bottlenecks.

Evaluation of heterogeneous benchmarks shows unevenness in capabilities.

Abstract

Recent approaches to evaluating Artificial General Intelligence (AGI) typically summarize a system's capability using the arithmetic mean of its proficiencies across multiple cognitive domains. While simple, this implicitly assumes compensability: exceptional performance in some areas can offset severe deficiencies in others. Genuine general intelligence, however, requires coherent sufficiency: balanced competence across all essential faculties. We introduce a coherence-based measure of AGI that integrates the generalized mean over a continuum of compensability exponents. This yields an area-under-the-curve (AUC) metric spanning arithmetic, geometric, and harmonic regimes, quantifying how robust an evaluated capability remains as compensability assumptions become stricter. Unlike the arithmetic mean, which rewards specialization, the AUC penalizes imbalance and exposes bottlenecks that constrain performance. To illustrate the framework, we apply it to cognitive profiles derived from the Cattell-Horn-Carroll (CHC) model, showing how coherence-based aggregation highlights imbalances that are obscured by arithmetic averaging. As a second, independent example, we apply the same methodology to a set of 17 heterogeneous benchmarks, demonstrating how coherence-based evaluation can reveal unevenness even in narrower task collections. These examples show that the proposed approach offers a principled, interpretable, and stricter foundation for measuring progress toward AGI.