On the Limits of Recursively Self-Improving AGI
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A system capable of complete self-referential at the outset may lose this capability as it evolves.
“Consequently, a system capable of complete self-referential at the outset may lose this capability as it evolves (Yampolskiy, 2015).”
From Gödel Agent: A Self-Referential Agent Framework for Recursively Self-Improvement (2025) · cites this paper as Yampolskiy, 2015
A system capable of complete self-referential at the outset may lose this capability as it evolves.
“Consequently, a system capable of complete self-referential at the outset may lose this capability as it evolves (Yampolskiy, 2015).”
From Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement (2024) · cites this paper as Yampolskiy, 2015
As the agent system becomes increasingly complex through self-optimization, it may require exponentially more intelligence to understand itself.
“Additionally, as the agent system becomes increasingly complex through self-optimization, it may require exponentially more intelligence to understand itself.”
From Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement (2024) · cites this paper as Yampolskiy, 2015
Cites
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486 · see citing works
No free lunch theorems for optimization
Wolpert, D. H., & Macready, W. G. (1997) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.585893 · Cited by 14,237 · see citing works
On computable numbers, with an application to the entscheidungsproblem
Turing, A. M. (1937) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s2-42.1.230 · Cited by 8,283 · see citing works
Journal of Consciousness Studies
(2022) · Journal of Consciousness Studies · doi:10.53765/20512201 · Cited by 6,852 · see citing works
Proceedings of the fifth Berkeley symposium on mathematical statistics and probability.
Kojima, K.-I. (1969) · Europe PMC (PubMed Central) · Cited by 3,648 · see citing works
Three approaches to the quantitative definition of information *
Kolmogorov, A. N. (1968) · International Journal of Computer Mathematics · doi:10.1080/00207166808803030 · Cited by 2,053 · see citing works
Superintelligence: paths, dangers, strategies
(2015) · Choice Reviews Online · doi:10.5860/choice.187536 · Cited by 1,999 · see citing works
Revue Internationale de Philosophie
Meyer, M. (2005) · Cited by 1,359 · see citing works
Ultimate physical limits to computation
Lloyd, S. (2000) · Nature · doi:10.1038/35023282 · Cited by 1,120 · see citing works
Ist die Trägheit eines Körpers von seinem Energieinhalt abhängig?
Einstein, A. (1905) · Annalen der Physik · doi:10.1002/andp.19053231314 · Cited by 1,042 · see citing works
Classes of recursively enumerable sets and their decision problems
Rice, H. G. (1953) · Transactions of the American Mathematical Society · doi:10.1090/s0002-9947-1953-0053041-6 · Cited by 869 · see citing works
Information, Physics, Quantum: The Search for Links
WHEELER, J. A. (2018) · CRC Press eBooks · doi:10.1201/9780429500459-19 · Cited by 749 · see citing works
Schaeffer, J., BURCH, N. R., Björnsson, Y., Kishimoto, A., Müller, M., Lake, R., Lu, P., & Sutphen, S. (2007) · Science · doi:10.1126/science.1144079 · Cited by 452 · see citing works
Guest Column: NP-complete problems and physical reality
Aaronson, S. (2005) · ACM SIGACT News · doi:10.1145/1052796.1052804 · Cited by 322 · see citing works
Proceedings of the London Mathematical Society
N., H. A. (1870) · Nature · doi:10.1038/002162b0 · Cited by 249 · see citing works
The Singularity: A Philosophical Analysis
Chalmers, D. J. (2016) · Science Fiction and Philosophy · doi:10.1002/9781118922590.ch16 · Cited by 246 · cited 3× · see citing works
“Fascinatingly, by analyzing properties which correlate with intelligence, Chalmers [30] is able to generalize self-improvement optimization to properties other than intelligence.”
BackgroundInformation in the Holographic Universe
Bekenstein, J. D. (2003) · Scientific American · doi:10.1038/scientificamerican0803-58 · Cited by 237 · see citing works
Does the Inertia of a Body Depend upon Its Energy Content? (1905)
Einstein, A. (2025) · Princeton University Press eBooks · doi:10.2307/jj.27710910.8 · Cited by 178 · see citing works
Artificial Intelligence Safety Engineering: Why Machine Ethics Is a Wrong Approach
Yampolskiy, R. V. (2012) · Studies in applied philosophy, epistemology and rational ethics · doi:10.1007/978-3-642-31674-6_29 · Cited by 126 · see citing works
Self-citationProceedings of the London Mathematical Society
(1879) · Nature · doi:10.1038/019527a0 · Cited by 124 · see citing works
Universal Algorithmic Intelligence: A Mathematical Top→Down Approach
Hütter, M. (2007) · Cognitive technologies · doi:10.1007/978-3-540-68677-4_8 · Cited by 83 · see citing works
Reoptimizing the traveling salesman problem
Archetti, C., Bertazzi, L., & Speranza, M. G. (2003) · Networks · doi:10.1002/net.10091 · Cited by 82 · see citing works
On the Hardness of Reoptimization
Böckenhauer, H.-J., Hromkovic̆, J., Mömke, T., & Widmayer, P. (2008) · Springer eBooks · doi:10.1007/978-3-540-77566-9_5 · Cited by 72 · see citing works
Turing Test as a Defining Feature of AI-Completeness
Yampolskiy, R. V. (2012) · Studies in computational intelligence · doi:10.1007/978-3-642-29694-9_1 · Cited by 71 · see citing works
Self-citationComplexity and Approximation in Reoptimization
Giorgio Ausiello, A., Vincenzo Bonifaci, A., & Escoffier, B. (2011) · IMPERIAL COLLEGE PRESS eBooks · doi:10.1142/9781848162778_0004 · Cited by 61 · see citing works
(1967) · Project Euclid (Cornell University) · Cited by 59 · see citing works
Utility function security in artificially intelligent agents
Yampolskiy, R. V. (2014) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2014.895114 · Cited by 47 · see citing works
Self-citationTowards a Theory of AI Completeness
Shahaf, D., & Eyal Amir, A. (2007) · Cited by 44 · see citing works
AI-Complete CAPTCHAs as Zero Knowledge Proofs of Access to an Artificially Intelligent System
Yampolskiy, R. V. (2011) · ISRN Artificial Intelligence · doi:10.5402/2012/271878 · Cited by 41 · see citing works
Self-citation(1999) · Cited by 39 · see citing works
Levels of Organization in General Intelligence
Yudkowsky, E. (2007) · Cognitive technologies · doi:10.1007/978-3-540-68677-4_12 · Cited by 38 · see citing works
Self-Modification and Mortality in Artificial Agents
Orseau, L., & Ring, M. B. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-22887-2_1 · Cited by 33 · see citing works
Fox, D. (2011) · Scientific American · doi:10.1038/scientificamerican0711-36 · Cited by 28 · see citing works
AI-Complete, AI-Hard, or AI-Easy - Classification of Problems in AI.
Yampolskiy, R. V. (2012) · Cited by 27 · see citing works
Self-citationEfficiency Theory : a Unifying Theory for Information, Computation and Intelligence
Yampolskiy, R. V. (2013) · Journal of Discrete Mathematical Sciences and Cryptography · doi:10.1080/09720529.2013.821361 · Cited by 25 · see citing works
Self-citationWhy an Intelligence Explosion is Probable
Loosemore, R. P. W., & Goertzel, B. (2012) · The frontiers collection · doi:10.1007/978-3-642-32560-1_5 · Cited by 25 · see citing works
Reoptimization of Minimum and Maximum Traveling Salesman’s Tours
Giorgio Ausiello, A., Escoffier, B., Monnot, J., & Paschos, V. T. (2006) · Lecture notes in computer science · doi:10.1007/11785293_20 · Cited by 24 · see citing works
Logical Theories for Agent Introspection
Bolander, T. (2004) · Cited by 23 · see citing works
Analysis of Types of Self-Improving Software
Yampolskiy, R. V. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-21365-1_39 · Cited by 21 · see citing works
Self-citationBostrom, N. (2006) · Cited by 19 · see citing works
Can Intelligence Explode?Preprint
Hütter, M. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1202.6177 · Cited by 17 · see citing works
Problems of Self-reference in Self-improving Space-Time Embedded Intelligence
Fallenstein, B., & Soares, N. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-09274-4_3 · Cited by 15 · see citing works
A Computability Argument Against Superintelligence
Wiedermann, J. (2012) · Cognitive Computation · doi:10.1007/s12559-012-9124-9 · Cited by 12 · see citing works
The No Free Lunch Theorem and hypothesis of instinctive animal behavior
Melkikh, A. V. (2014) · Artificial Intelligence Research · doi:10.5430/air.v3n4p43 · Cited by 11 · see citing works
Toward a Standard Metric of Machine Intelligence
Yonck, R. (2012) · World Futures Review · doi:10.1177/194675671200400210 · Cited by 10 · see citing works
Construction of an NP Problem with an Exponential Lower BoundPreprint
Yampolskiy, R. V. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1111.0305 · Cited by 8 · see citing works
Self-citationThe Universe of MindsPreprint
Yampolskiy, R. V. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.0369 · Cited by 6 · see citing works
Self-citationHall, J. (2008) · Artificial General Intelligence · Cited by 6 · see citing works
A Model for Recursively Self Improving Programs
Mahoney, M. B. (2010) · Cited by 3 · see citing works
Computing Partial Solutions to Difficult AI Problems
Yampolskiy, R. V. (2012) · Cited by 2 · see citing works
Self-citation
Flagged first, then by citations
4 of the 54 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Unethical Research: How to Create a Malevolent Artificial IntelligencePreprint
Pistono, F., & Yampolskiy, R. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.02817 · Cited by 51 · see citing works
Self-citationTaxonomy of Pathways to Dangerous Artificial Intelligence
Yampolskiy, R. V. (2016) · ThinkIR: The University of Louisville's Institutional Repository (University of Louisville) · Cited by 41 · see citing works
Self-citationCollective hybrid intelligence: towards a conceptual framework
Moradi, M., Moradi, M., Bayat, F., & Toosi, A. N. (2019) · International Journal of Crowd Science · doi:10.1108/ijcs-03-2019-0012 · Cited by 41 · see citing works
What are the ultimate limits to computational techniques: verifier theory and unverifiability
Yampolskiy, R. V. (2017) · Physica Scripta · doi:10.1088/1402-4896/aa7ca8 · Cited by 26 · see citing works
Self-citationOn the Controllability of Artificial Intelligence: An Analysis of Limitations
Yampolskiy, R. V. (2022) · Journal of Cyber Security and Mobility · doi:10.13052/jcsm2245-1439.1132 · Cited by 49 · see citing works
Self-citationAnalysis of Types of Self-Improving Software
Yampolskiy, R. V. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-21365-1_39 · Cited by 21 · see citing works
Self-citationYampolskiy, R. V. (2018) · Information · doi:10.3390/info9080190 · Cited by 16 · see citing works
Self-citationOn the origin of synthetic life: attribution of output to a particular algorithm
Yampolskiy, R. V. (2016) · Physica Scripta · doi:10.1088/0031-8949/92/1/013002 · Cited by 16 · see citing works
Self-citationTaxonomy of Pathways to Dangerous AIPreprint
Yampolskiy, R. V. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.03246 · Cited by 15 · see citing works
Self-citationQuantum Metalanguage and The New Cognitive Synthesis
Melkikh, A. V., Khrennikov, A., & Yampolskiy, R. V. (2019) · NeuroQuantology · doi:10.14704/nq.2019.17.1.1904 · Cited by 8 · see citing works
Self-citationOn Controllability of AIPreprint
Yampolskiy, R. V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04071 · Cited by 8 · see citing works
Self-citationGödel Agent: A Self-Referential Agent Framework for Recursively Self-Improvement
Yin, X., Wang, X., Pan, L., Lin, L., Wan, X., & Wang, W. Y. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.1354 · Cited by 5 · see citing works
Diminishing Returns and Recursive Self Improving Artificial Intelligence
Majot, A. M., & Yampolskiy, R. V. (2017) · The frontiers collection · doi:10.1007/978-3-662-54033-6_7 · Cited by 5 · see citing works
Self-citationSajduk, B. (2019) · The Copernicus Journal of Political Studies · doi:10.12775/cjps.2019.017 · Cited by 4 · see citing works
Entropic boundary conditions towards safe artificial superintelligence
Núñez-Corrales, S., & Jakobsson, E. (2021) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2021.1952653 · Cited by 3 · see citing works
Yampolskiy, R. V. (2022) · Studies in applied philosophy, epistemology and rational ethics · doi:10.1007/978-3-031-09153-7_18 · Cited by 3 · see citing works
Self-citationYampolskiy, R. V. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-19907-3_44 · Cited by 3 · see citing works
Self-citationVerifier Theory and UnverifiabilityPreprint
Yampolskiy, R. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.00331 · Cited by 3 · see citing works
Self-citationGödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
Yin, X., Wang, X., Pan, L., Lin, L., Wan, X., & Wang, W. Y. (2024) · arXiv · doi:10.48550/arxiv.2410.04444 · Cited by 2 · see citing works
“Consequently, a system capable of complete self-referential at the outset may lose this capability as it evolves (Yampolskiy, 2015).”
Uncontrollability of Artificial Intelligence.
Yampolskiy, R. V. (2021) · International Joint Conference on Artificial Intelligence · Cited by 1 · see citing works
Self-citationAbout the Taxonomy of Autonomous Agents
Yalovets, A. L. (2018) · Èlektronnoe modelirovanie · doi:10.15407/emodel.40.01.003
AI Risk Skepticism.Preprint
Yampolskiy, R. V. (2021) · arXiv (Cornell University)
Self-citationDeconstructing Superintelligence: Identity, Self-Modification and Différance
Perrier, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-33195-3_14
Cleverly, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7273118
iBRAHIMOĞLU, N., Demi̇rezen, M. U., & Yıldız, F. (2026) · Cluster Computing · doi:10.1007/s10586-026-06537-4
- Authors
- Yampolskiy, R. V.
- Affiliations
- University of Louisville (US)
- Corresponding author
- Yampolskiy, Roman V.
- ORCID
- Yampolskiy, Roman V.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2015
- Pages
- 394-403
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2406968617
- Cited by
- 23
- References
- 54
- Citations by year
- 2026: 3 · 2023: 1 · 2022: 2 · 2021: 3 · 2020: 1 · 2019: 3 · 2018: 2 · 2017: 2 · 2016: 4 · 2015: 2
- FWCI
- 3.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computability, Logic, AI Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- artificial general intelligence, limits of computation, convergence theory, self-improving AI
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
