CoChat

Self-Referential Introspection in Large Language Models: The Critical Threshold for Recursive Self-Improvement

Open access
Zhang, Jiang, Yuan, Bing, Zhang, Qian · 2026 · Entropy

The DOI matches its Crossref record; 57 of the 61 references it cites were found in a registry or an index, and 3 are not checked yet; 41 of the 84 sources its claims cite were checked for support.

Abstract

The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative? Drawing an analogy to von Neumann’s complexity threshold for self-reproducing automata, we argue that sustainable recursive self-improvement in large language models (LLMs) requires a functional analogue: introspection—the system’s capacity to simulate its own operations and target modifications. Grounded in Kleene’s Second Recursion Theorem, we construct such introspective self-improvement programs and prove their key properties: completeness of self-modification, necessity of the reflective architecture, undecidability of improvement in general, and equivalence with Schmidhuber’s Gödel machine under a rewrite-equivalence notion, which transfers the global optimality guarantee. An empirical review, organized around these functional criteria, suggests that current LLMs exhibit only quasi-introspection.The available evidence does not establish complete introspection in the formal sense developed here, while pointing to several candidate structural bottlenecks, including incomplete self-access, feedforward processing, and limited computational depth. We outline architectural paths toward the threshold and discuss the safety implications of crossing it.

Verified 2026-11-19 · 3 references not checked yet

Overview

CoChat Summary

TL;DR

The paper argues that sustained recursive self-improvement in LLMs requires a formal introspection threshold—an effective self-model capable of simulating and modifying its own operations—analogous to von Neumann’s complexity threshold. It constructs introspective self-improvement programs via Kleene’s Second Recursion Theorem and reviews empirical evidence, concluding current LLMs show only quasi-introspection and have not been shown to cross the threshold.

Key findings

  • Using Kleene’s Second Recursion Theorem, the paper constructs an introspection program \(e^*\) with \(\varphi_{e^*}\simeq\varphi_{f_T(e^*)}\), and an introspective self-improvement program \(\omega\) with \(\varphi_\omega\simeq\varphi_{M\circ V\circ f_T(\omega)}\); the first such program is treated as the threshold analogous to von Neumann’s complexity threshold.
  • Formal properties include completeness of self-modification (Theorem A1), necessity of the reflective architecture (Theorem A2), undecidability of improvement in general (Theorem A3, via Rice’s theorem), and equivalence with Schmidhuber’s Gödel machine under a rewrite-equivalence notion, transferring the global optimality guarantee (Theorem A4/A5).
  • The empirical review concludes current LLMs exhibit only quasi-introspection: fragmentary, approximate, domain-specific self-knowledge lacking the completeness, reliability, and causal grounding required by the formal definition. Candidate bottlenecks include incomplete self-access, feedforward processing—log-precision Transformers are bounded by uniform TC0—and limited computational depth; self-reports may lack causal grounding.
  • Cited evidence includes Self-Refine plateauing after a few iterations, Song et al. finding no privileged self-access across 21 LLMs, and safety implications: if the threshold is crossable, completeness means safety constraints within the source are reachable and rewritable, so Corollary A1 requires an enforcement boundary outside the program’s write perimeter.

Methods

  • Theoretical/computability construction: analogizes von Neumann’s self-reproducing automata and Quine programs, then uses Kleene’s Second Recursion Theorem to define introspection and introspective self-improvement programs; formal properties are proved in appendices.
  • Empirical review: surveys literature from 2022–2026 organized around four functional properties—self-modeling, self-simulation, self-evaluation, self-modification—and structural properties of reflexivity and recurrent processing, distinguishing behavioral reports from architectural evidence.
  • No new experiments are reported; the analysis combines formal proofs, comparison with the Gödel machine, and a literature-based assessment of current LLMs.

Limitations

  • Stated: the formal results establish properties of explicitly defined introspective programs, while their applicability to contemporary LLM architectures remains conditional and empirically unresolved; the paper does not claim a universal scalar metric for LLM complexity or threshold.
  • Stated: the necessity claim does not guarantee monotonically increasing empirical performance, which depends on the evaluation function, modification operator, objective, and viability conditions; the empirical survey is not intended to directly test or verify the formal framework.
  • Evident: the paper reports no original empirical data and relies on cited studies, including preliminary/preprint evidence and conflicting findings on privileged self-access; the formal existence proof is conditional on a bounded simulation horizon \(T\).

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/e28090951

Cites

57 of 61 references verified0 citation errors · 1 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Recursive self-improvement and introspection in current LLMs. The diagram relates recursive self-improvement to complexity and introspection thresholds, summarizes evidence for quasi-introspective capabilities in current LLMs, and distinguishes proposed structural limitations from corresponding research directions. Dashed lines denote the proposed introspection threshold. For the corresponding references, see [4,25,26].
Figure 1 Recursive self-improvement and introspection in current LLMs. The diagram relates recursive self-improvement to complexity and introspection thresholds, summarizes evidence for quasi-introspective capabilities in current LLMs, and distinguishes proposed structural limitations from corresponding research directions. Dashed lines denote the proposed introspection threshold. For the corresponding references, see [4,25,26].CC BY · From the PDF
Self-Reference: the machine (A+B+C) and its description (φ) form a reflexive pair — the core of von Neumann's complexity threshold
Self-Reference: the machine (A+B+C) and its description (φ) form a reflexive pair — the core of von Neumann's complexity thresholdCC BY · From the PDF
Figure 3 Self-reference: from Quine to introspective Self-improvement. The dashed lines indicate the correspondence between modules.
Figure 3 Self-reference: from Quine to introspective Self-improvement. The dashed lines indicate the correspondence between modules.CC BY · From the PDF
The first introspective self-improved program S0 is the threshold — beyond it, recursive self-improvement is automatic
The first introspective self-improved program S0 is the threshold — beyond it, recursive self-improvement is automaticCC BY · From the PDF

Verification

Claims the paper makes

31 Valid · 10 Not valid · 33 Not checked · 99 Own results and interpretations

93 more claims · 21 with their cited sources checked

Create a free account to see all 173 claims and to verify the 1 reference still open.

See all claims — free account
  • Probably not a substantial claim. 42
  • It may state two separate claims as one. 48

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

  • Self-Refine: Iterative Refinement with Self-Feedback

    Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.17651 · Cited by 2,314 · cited 4×

    “Empirically, Self-Refine [7] and Reflexion [6] operate at the prompt/context layer through textual self-critique.”
    Influential
  • Three approaches to the quantitative definition of information*

    Kolmogorov, A. N. (1968) · International Journal of Computer Mathematics · doi:10.1080/00207166808803030 · Cited by 2,031 · cited 2×

    “With modern notions of Kolmogrov complexity [18] and algorithmic information entropy [19], the complexity threshold can be quantified by the minimum description length of a self-reproducing automaton.”
  • Reflexion: Language Agents with Verbal Reinforcement Learning

    Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · cited 2×

    “Empirically, Self-Refine [7] and Reflexion [6] operate at the prompt/context layer through textual self-critique.”
  • Two concepts of consciousness

    Rosenthal, D. M. (1986) · Philosophical Studies · doi:10.1007/bf00355521 · Cited by 1,019 · cited 1×

    “Higher-Order Thought (HOT) theory [75] identifies consciousness with higher-order representations of one’s own mental states—a structure formally close to what we call introspection.”
  • On the Length of Programs for Computing Finite Binary Sequences

    Chaitin, G. J. (1966) · Journal of the ACM · doi:10.1145/321356.321363 · Cited by 913 · cited 2×

    “With modern notions of Kolmogrov complexity [18] and algorithmic information entropy [19], the complexity threshold can be quantified by the minimum description length of a self-reproducing automaton.”
  • AI models collapse when trained on recursively generated data

    Shumailov, I., Shumaylov, Z., Zhao, Y., Papernot, N., Anderson, R., & Gal, Y. (2024) · Nature · doi:10.1038/s41586-024-07566-y · Cited by 793 · cited 2×

    “Another critical obstacle to sustained self-improvement in LLMs is model collapse —a degenerative process wherein successive generations of generative models are progressively polluted by their own synthetic outputs [14].”
  • On Notation for Ordinal Numbers

    Kleene, S. C. (1938) · Journal of Symbolic Logic · doi:10.2307/2267778 · Cited by 758 · cited 1×

    “The deeper mathematical foundation for self-reference in computation is provided by Kleene’s Second Recursion Theorem [23,37].”
  • Speculations Concerning the First Ultraintelligent Machine

    Good, I. J. (1966) · Advances in Computers · doi:10.1016/s0065-2458(08)60418-0 · Cited by 703 · cited 3×

    “…Recursive Self-Improvement The hypothesis that machine intelligence could surpass human capabilities and trigger runaway growth dates back to Good [4], who observed that an ultraintelligent machine” could design increasingly superior systems, culminating in what he termed an intelligence…”
  • Self-reproduction in cellular automata

    Langton, C. G. (1984) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(84)90256-2 · Cited by 571 · cited 2×

    “This tension is epitomized by the historical debate on the necessity of universal constructors in self-reproducing automata [39–41]; while von Neumann’s open-ended replication relies on a universal constructor to support arbitrary mutant structures, self-reproducing loops can be implemented far…”
  • LLM Evaluators Recognize and Favor Their Own Generations

    Panickssery, A., Bowman, S. R., & Feng, S. (2024) · arXiv · doi:10.48550/arxiv.2404.13076 · Cited by 559 · cited 1×

    “Conversely, this internal model exhibits a functional yet biased form of self-recognition: Panickssery et al. [59] showed that LLMs can distinguish their own outputs from human or exter-nal ones with non-trivial accuracy, a capability that correlates linearly with an intrinsic self-preference bias.”

Show all 61 references

Research works printed but not linked: 17

  1. Huang J. Chen X. Mishra S. Zheng H.S. Yu A.W. Song X. Zhou D. Large Language Models Cannot Self-Correct Reasoning Yet Proceedings of the Twelfth International Conference on Learning Representations Vienna, Austria 7–11 May 2024
  2. Burks A.W. Theory of Self-Reproducing Automata (John von Neumann) University of Illinois Press Champaign, IL, USA 1966
  3. Rogers H. Theory of Recursive Functions and Effective Computability MIT Press Cambridge, MA, USA 1967
  4. Zelikman E. Lorch E. Mackey L. Kalai A.T. Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation Proceedings of the COLM 2024, Philadelphia, PA, USA 7–9 October 2024
  5. Bolander T. Logical Theories for Agent Introspection Ph.D. Thesis Technical University of Denmark Kongens Lyngby, Denmark 2003
  6. Ferrando J. Obeso O. Rajamanoharan S. Nanda N. Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models Proceedings of the ICLR 2025 Singapore 24–28 April 2025
  7. Binder F.J. Chua J. Korbak T. Sleight H. Hughes J. Long R. Perez E. Turpin M. Evans O. Looking Inward: Language Models Can Learn About Themselves by Introspection Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025) Singapore 24–28 April 2025
  8. Song S. Hu J. Mahowald K. Language Models Fail to Introspect About Their Knowledge of Language Proceedings of the Conference on Language Modeling (COLM) Montreal, QC, Canada 7–10 October 2025
  9. Betley J. Bao X. Soto M. Sztyber-Betley A. Chua J. Evans O. Tell Me About Yourself: LLMs Are Aware of Their Learned Behaviors Proceedings of the Thirteenth International Conference on Learning Representations (ICLR) Singapore 24–28 April 2025
  10. Merrill W. Sabharwal A. The Expressive Power of Transformers with Chain of Thought Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024) Vienna, Austria 7–11 May 2024
  11. Dehghani M. Gouws S. Vinyals O. Uszkoreit J. Kaiser Ł. Universal Transformers Proceedings of the ICLR 2019, New Orleans, LA, USA 6–9 May 2019
  12. Hao S. Sukhbaatar S. Su A. Li X. Hu Z. Weston J. Tian Y. Training Large Language Models to Reason in a Continuous Latent Space Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025) Singapore 24–28 April 2025
  13. Jaegle A. Gimeno F. Brock A. Zisserman A. Vinyals O. Carreira J. Perceiver: General Perception with Iterative Attention Proceedings of the ICML 2021 Virtual 18–24 July 2021
  14. Baars B.J. A Cognitive Theory of Consciousness Cambridge University Press New York, USA 1988
  15. Mahoney, M. (2026, July 10). A Model for Recursively Self Improving Programs, 2010. Self-Published Preprint (Final Version v.3, December 2010)
  16. Mahoney M. A Model for Recursively Self Improving Programs, 2010. Self-Published Preprint (Final Version v.3, December 2010); An Earlier Version Was Submitted to the Journal of Artificial General Intelligence in 2008 Available online: https://www.academia.edu/66745654/A_Model_for_Recursively_Self_Improving_Programs (accessed on 10 July 2026)
  17. Nivel E. Thórisson K.R. Steunebrink B.R. Dindo H. Pezzulo G. Rodríguez M. Hernández C. Ognibene D. Schmidhuber J. Sanz R. Bounded Recursive Self-Improvement Proceedings of the AGI 2013 Beijing, China 31 July–3 August 2013

Cited by

Metadata

Authors
Zhang, J., Yuan, B., & Zhang, Q.
Affiliations
  • Beijing Normal University (CN)
  • Swarma Research (CN)
Corresponding author
Zhang, Jiang
Venue
Entropy
Publisher
MDPI AG
Published
2026-08-24
Volume
28
Issue
9
Pages
951
ISSN
1099-4300 (ISSN-L)
OpenAlex
W7204071795
Cited by
2
References
31
Citations by year
2026: 2
FWCI
4.99
Type
journal article
Language
en
Open access
Locations
  • Entropy (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Computability, Logic, AI Algorithms
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › semigroups and automata theory
  • Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
Keywords
self-reflection, large language models, recursive self-improvement, self-modification, self-reproducing automata, undecidability, AI safety, reflective architecture

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.