A Definition of AGI

作者：Dan Hendrycks, Dawn Song, Christian Szegedy, Honglak Lee, Yarin Gal, Erik Brynjolfsson, Shaoping Li, Andy Zou, Lionel Levine, Bo Han, Jie Fu, Ziwei Liu, Shin, Jinwoo, Kimin Lee, Mantas Mazeika, Long Phan, George Ingebretsen, Adam Khoja, Xie, Cihang, Olawale Salaudeen, Matthias Hein, Kevin Zhao, Alexander Pan, David Duvenaud, Bo Li, Steve Omohundro, Gabriel Alfour, Max Tegmark, Kevin S. McGrew, Gary Marcus, Jaan Tallinn, Eric Schmidt, Yoshua Bengio · 发表于：arXiv (Cornell University) · 年份：2025 · DOI：10.48550/arxiv.2510.18212 · 被引用次数：2 · 研究领域：Cognitive Abilities and Testing、Computability, Logic, AI Algorithms、Cognitive Computing and Networks

The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult. To operationalize this, we ground our methodology in Cattell-Horn-Carroll theory, the most empirically validated model of human cognition. The framework dissects general intelligence into ten core cognitive domains-including reasoning, memory, and perception-and adapts established human psychometric batteries to evaluate AI systems. Application of this framework reveals a highly "jagged" cognitive profile in contemporary models. While proficient in knowledge-intensive domains, current AI systems have critical deficits in foundational cognitive machinery, particularly long-term memory storage. The resulting AGI scores (e.g., GPT-4 at 27%, GPT-5 at 57%) concretely quantify both rapid progress and the substantial gap remaining before AGI.