Measuring Progress Toward AGI: A Cognitive Framework
Not on the map. Why?
Abstract (arXiv)
Despite widespread discussion of AGI, there is no clear framework for measuring progress toward it. This ambiguity fuels subjective claims, makes it difficult to track progress, and risks hindering responsible governance. As a starting point to address this gap, we present a framework for understanding system capabilities in relation to human cognitive abilities. Drawing from decades of research in psychology, neuroscience, and cognitive science, we introduce a Cognitive Taxonomy that deconstructs general intelligence into 10 key cognitive faculties. We then propose a rigorous evaluation protocol in which a system's performance is measured across a suite of targeted, held-out cognitive tasks, generating a 'cognitive profile' that can be used to understand a system's strengths and weaknesses. We hope this framework will provide a practical roadmap and an initial step toward more rigorous, empirical evaluation of AGI.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 17 of its 171 references that are in the map. First posted on arXiv 27 May 2026.
Builds on
17 of 171 references.
References · 17
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
- 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 310
- 2019Abductive Commonsense Reasoningcited by 300
- 2022Language models show human-like content effects on reasoning taskscited by 171
- 2025ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systemscited by 171
- 2025GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Taskscited by 142
- 2023Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarkscited by 139
- 2023Levels of AGI for Operationalizing Progress on the Path to AGIcited by 94
- 2025SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledgecited by 44
- 2020Meta-learning in natural and artificial intelligencecited by 39
- 2016The AGI Containment Problemcited by 36
- 2025A Definition of AGIcited by 25
5 more
- 2024Large Language Models Lack Understanding of Character Composition of Wordscited by 21
- 2025Remote Labor Index: Measuring AI Automation of Remote Workcited by 18
- 2025The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factualitycited by 14
- 2026Evaluating Alignment of Behavioral Dispositions in LLMscited by 6
- 2026Capabilities Ain't All You Need: Measuring Propensities in AIcited by 6
Built on by
Citing papers per year: 2026: 6.
6 papers.
- 2026CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Modelcited by 0
- 2026Epistemic Stance Flexibility Probing: Measuring Prompt-Conditioned Register Shift in Large Language Modelscited by 0
- 2026The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systemscited by 0
- 2026Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model Familiescited by 0
- 2026Using profiles of cognitive capability to assess AI suitability for workplace taskscited by 0
- 2026Thought without systematicity? Evaluating reasoning models on rule induction taskscited by 0
- 2026Thought without systematicity? Evaluating reasoning models on rule induction tasks12 Sep 2026
- 2026Using profiles of cognitive capability to assess AI suitability for workplace tasks26 Aug 2026
- 2026Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model Families27 Jul 2026
- 2026The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems20 Jul 2026
- 2026Epistemic Stance Flexibility Probing: Measuring Prompt-Conditioned Register Shift in Large Language Models14 Jul 2026
- 2026CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model4 Jun 2026