mlsanityData to 14 Oct 2026

Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics

arXiv 2606.08267 ↗First posted 6 Jun 2026cs.GT cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The classical Second Welfare Theorem decentralizes any Pareto efficient allocation through prices and transfers under convexity and regularity. In post AGI economies, autonomy rights, self-modification, identity continuity, and superposed preferences need not behave as commodities or define a stable welfare relation, so this reduction may fail even when a supporting hyperplane exists. We give an autonomy-qualified Second Welfare Theorem stating the joint conditions convexity, stable moral status, non-fungible rights, welfare selection, non manipulation, governed self modification, and verification under which an autonomy Pareto optimum remains certifiably decentralizable, distinguishing economic preference superposition, a hypothesis about context-indexed choice, from neural feature superposition.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 64 references that are in the map. First posted on arXiv 6 Jun 2026.

Builds on

32 of 64 references.

References · 32

  1. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  2. 2017Deep reinforcement learning from human preferencescited by 3,912
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  4. 2016Concrete Problems in AI Safetycited by 1,642
  5. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  6. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  7. 2022Toy Models of Superpositioncited by 971
  8. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
  9. 2024Scaling and evaluating sparse autoencoderscited by 553
  10. 2020Artificial Intelligence, Values and Alignmentcited by 448
  11. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  12. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
20 more
  1. 2024Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2cited by 394
  2. 2016Cooperative Inverse Reinforcement Learningcited by 300
  3. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 258
  4. 2017Inverse Reward Designcited by 249
  5. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  6. 2024Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoderscited by 143
  7. 2024Emergent social conventions and collective bias in LLM populationscited by 123
  8. 2023Consciousness in Artificial Intelligence: Insights from the Science of Consciousnesscited by 104
  9. 2024Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedbackcited by 100
  10. 2023Scheming AIs: Will AIs fake alignment during training in order to get power?cited by 97
  11. 2023Could a Large Language Model be Conscious?cited by 73
  12. 2018Incomplete Contracting and AI Alignmentcited by 62
  13. 2026Emotion Concepts and their Function in a Large Language Modelcited by 57
  14. 2024Taking AI Welfare Seriouslycited by 31
  15. 2025Superposition Yields Robust Neural Scalingcited by 31
  16. 2023Market Concentration Implications of Foundation Modelscited by 15
  17. 2024Scenarios for the Transition to AGIcited by 13
  18. 2024Economic Policy Challenges for the Age of AIcited by 6
  19. 2026Post-AGI Economies: Autonomy and the First Fundamental Theorem of Welfare Economicscited by 2
  20. 2026Deconstructing Superintelligence: Identity, Self-Modification and Diff'erancecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026A New Theory of Value for Post-AGI Economicscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning
  2. 2026EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and Experiments
  3. 2026A General Equilibrium Theory of Orchestrated AI Agent Systems
  4. 2026Alignment of a Total Automation Economy
  5. 2026The Human Utility Factor: A Computable Welfare Metric That Reframes AI Governance as a Constrained Optimisation Problem
  6. 2026The economic alignment problem of artificial intelligence ↗
  7. 2025Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
  8. 2026A Survey of Reinforcement Learning For Economics