mlsanityData to 7 Oct 2026

Levels of AGI for Operationalizing Progress on the Path to AGI

arXiv 2311.02462 ↗First posted 4 Nov 2023cs.AIcited by 94

Not on the map. Why?

Abstract (arXiv)

We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors. This framework introduces levels of AGI performance, generality, and autonomy, providing a common language to compare models, assess risks, and measure progress along the path to AGI. To develop our framework, we analyze existing definitions of AGI, and distill six principles that a useful ontology for AGI should satisfy. With these principles in mind, we propose "Levels of AGI" based on depth (performance) and breadth (generality) of capabilities, and reflect on how current systems fit into this ontology. We discuss the challenging requirements for future benchmarks that quantify the behavior and capabilities of AGI models against these levels. Finally, we discuss how these levels of AGI interact with deployment considerations such as autonomy and risk, and emphasize the importance of carefully selecting Human-AI Interaction paradigms for responsible and safe deployment of highly capable AI systems.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 28 of its 86 references that are in the map. First posted on arXiv 4 Nov 2023.

Builds on

28 of 86 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  7. 2022Emergent Abilities of Large Language Modelscited by 2,483
  8. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  9. 2023PaLM 2 Technical Reportcited by 1,154
  10. 2018Model Cards for Model Reportingcited by 1,068
  11. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  12. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
16 more
  1. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 340
  2. 2022Emergent Analogical Reasoning in Large Language Modelscited by 239
  3. 2020Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthycited by 182
  4. 2023GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Modelscited by 174
  5. 2021Alignment of Language Agentscited by 167
  6. 2023Model evaluation for extreme riskscited by 167
  7. 2023Personality Traits in Large Language Modelscited by 166
  8. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  9. 2023Consciousness in Artificial Intelligence: Insights from the Science of Consciousnesscited by 99
  10. 2023Managing extreme AI risks amid rapid progresscited by 48
  11. 2022The Turing Trap: The Promise & Peril of Human-Like Artificial Intelligencecited by 42
  12. 2021From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligencecited by 35
  13. 2023Scientists' Perspectives on the Potential for Generative AI in their Fieldscited by 22
  14. 2023The Design Space of Generative Modelscited by 9
  15. 2021Qualitative Analysis for Human Centered AIcited by 4
  16. 2022Which one is more toxic? Findings from Jigsaw Rate Severity of Toxic Commentscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 30; 2025: 38; 2026: 21.

94 papers.

Sort:

By area:

  1. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  2. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmarkcited by 281
  3. 2024MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIcited by 192
  4. 2025Cosmos-Reason1: From Physical Common Sense To Embodied Reasoningcited by 159
  5. 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilitiescited by 127
  6. 2024Cradle: Empowering Foundation Agents Towards General Computer Controlcited by 114
  7. 2025LLM Social Simulations Are a Promising Research Methodcited by 97
  8. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  9. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 79
  10. 2025Levels of Autonomy for AI Agentscited by 45
  11. 2024MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videoscited by 43
  12. 2025Fully Autonomous AI Agents Should Not be Developedcited by 43
38 more
  1. 2023LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystemcited by 35
  2. 2024Benchmarks as Microscopes: A Call for Model Metrologycited by 33
  3. 2024Towards evaluations-based safety cases for AI schemingcited by 32
  4. 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
  5. 2024AI Safety in Generative AI Large Language Models: A Surveycited by 31
  6. 2024Taking AI Welfare Seriouslycited by 28
  7. 2024Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Criticcited by 27
  8. 2025Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agentscited by 23
  9. 2024I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBenchcited by 20
  10. 2025Towards Agentic AI Networking in 6G: A Generative Foundation Model-as-Agent Approachcited by 19
  11. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  12. 2025I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactionscited by 17
  13. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challengescited by 14
  14. 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Modelscited by 13
  15. 2025MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Modelscited by 13
  16. 2024Boundless Socratic Learning with Language Gamescited by 12
  17. 2024The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignmentcited by 11
  18. 2025OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Modelscited by 9
  19. 2024Towards Building Specialized Generalist AI with System 1 and System 2 Fusioncited by 8
  20. 2025Thinking Preference Optimizationcited by 8
  21. 2023Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifestocited by 7
  22. 2025MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactionscited by 7
  23. 2024Levels of AI Agents: from Rules to Large Language Modelscited by 6
  24. 2024Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructionscited by 6
  25. 2025OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?cited by 6
  26. 2025FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challengingcited by 6
  27. 2026AI Must Embrace Specialization via Superhuman Adaptable Intelligencecited by 6
  28. 2026Measuring Progress Toward AGI: A Cognitive Frameworkcited by 6
  29. 2023An Evaluation of GPT-4V and Gemini in Online VQAcited by 5
  30. 2024Crafting Knowledge: Exploring the Creative Mechanisms of Chat-Based Search Enginescited by 5
  31. 2024On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know'cited by 5
  32. 2025L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Executioncited by 5
  33. 2025Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasonerscited by 5
  34. 2025SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6Gcited by 5
  35. 2026AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinkingcited by 5
  36. 2024Generative AI Security: Challenges and Countermeasurescited by 4
  37. 2024Deploying Foundation Model Powered Agent Services: A Surveycited by 4
  38. 2025Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspectivecited by 4

50 most cited of 94 All 94 (JSON)