mlsanityData to 7 Oct 2026

AGI Safety Literature Review

arXiv 1805.01109 ↗First posted 3 May 2018cs.AIcited by 28

Not on the map. Why?

Abstract (arXiv)

The development of Artificial General Intelligence (AGI) promises to be a major event. Along with its many potential benefits, it also raises serious safety concerns (Bostrom, 2014). The intention of this paper is to provide an easily accessible and up-to-date collection of references for the emerging field of AGI safety. A significant number of safety problems for AGI have been identified. We list these, and survey recent research on solving them. We also cover works on how best to think of AGI from the limited knowledge we have today, predictions for when AGI will first be created, and what will happen after its creation. Finally, we review the current public policy on AGI.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 7; 2022: 6; 2023: 3; 2024: 2; 2025: 8; 2026: 1.

28 papers.

Sort:

By area:

  1. 2018Scalable agent alignment via reward modeling: a research directioncited by 438
  2. 2022The Alignment Problem from a Deep Learning Perspectivecited by 246
  3. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  4. 2021Alignment of Language Agentscited by 167
  5. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  6. 2021Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)cited by 55
  7. 2023LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recoverycited by 37
  8. 2021A Survey on AI Assurancecited by 16
  9. 2022Current and Near-Term AI as a Potential Existential Risk Factorcited by 14
  10. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challengescited by 14
  11. 2021Impossibility Results in AI: A Surveycited by 13
  12. 2025Distributional AGI Safetycited by 8
16 more
  1. 2021Explicit Explore, Exploit, or Escape (E4): near-optimal safety-constrained reinforcement learning in polynomial timecited by 6
  2. 2025Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impactcited by 6
  3. 2022Should attention be all we need? The epistemic and ethical implications of unification in machine learningcited by 4
  4. 2024Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignmentcited by 3
  5. 2021Counterfactual Planning in AGI Systemscited by 2
  6. 2025Why do Experts Disagree on Existential Risk and P(doom)? A Survey of AI Expertscited by 2
  7. 2021AI Risk Skepticismcited by 1
  8. 2022Technology and Consciousnesscited by 1
  9. 2023The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forwardcited by 1
  10. 2024The Elephant in the Room -- Why AI Safety Demands Diverse Teamscited by 1
  11. 2025Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimizationcited by 1
  12. 2025Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Modelscited by 1
  13. 2022Exploring the Constraints on Artificial General Intelligence: A Game-Theoretic No-Go Theoremcited by 0
  14. 2025Towards Integrated Alignmentcited by 0
  15. 2025Individual utilities of life satisfaction reveal inequality aversion unrelated to political alignmentcited by 0
  16. 2026Sustaining AI safety: Control-theoretic external impossibility, intrinsic necessity, and structural requirementscited by 0