How Metacognitive Architectures Remember Their Own Thoughts: A Systematic Review
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912460959645696 |
|---|---|
| author | Nolte, Robin Pomarlan, Mihai Janssen, Ayden Beßler, Daniel Javanmardi, Kamyar Jongebloed, Sascha Porzel, Robert Bateman, John Beetz, Michael Malaka, Rainer |
| author_facet | Nolte, Robin Pomarlan, Mihai Janssen, Ayden Beßler, Daniel Javanmardi, Kamyar Jongebloed, Sascha Porzel, Robert Bateman, John Beetz, Michael Malaka, Rainer |
| contents | Background: Metacognition has gained significant attention for its potential to enhance autonomy and adaptability of artificial agents but remains a fragmented field: diverse theories, terminologies, and design choices have led to disjointed developments and limited comparability across systems. Existing overviews remain at a conceptual level that is undiscerning to the underlying algorithms, representations, and their respective success.
Methods: We address this gap by performing an explorative systematic review. Reports were included if they described techniques enabling Computational Metacognitive Architectures (CMAs) to model, store, remember, and process their episodic metacognitive experiences, one of Flavell's (1979a) three foundational components of metacognition. Searches were conducted in 16 databases, consulted between December 2023 and June 2024. Data were extracted using a 20-item framework considering pertinent aspects.
Results: A total of 101 reports on 35 distinct CMAs were included. Our findings show that metacognitive experiences may boost system performance and explainability, e.g., via self-repair. However, lack of standardization and limited evaluations may hinder progress: only 17% of CMAs were quantitatively evaluated regarding this review's focus, and significant terminological inconsistency limits cross-architecture synthesis. Systems also varied widely in memory content, data types, and employed algorithms.
Discussion: Limitations include the non-iterative nature of the search query, heterogeneous data availability, and an under-representation of emergent, sub-symbolic CMAs. Future research should focus on standardization and evaluation, e.g., via community-driven challenges, and on transferring promising principles to emergent architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13467 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How Metacognitive Architectures Remember Their Own Thoughts: A Systematic Review Nolte, Robin Pomarlan, Mihai Janssen, Ayden Beßler, Daniel Javanmardi, Kamyar Jongebloed, Sascha Porzel, Robert Bateman, John Beetz, Michael Malaka, Rainer Neurons and Cognition Artificial Intelligence I.2.0; I.2.4; I.2.6; I.2.8; J.4 Background: Metacognition has gained significant attention for its potential to enhance autonomy and adaptability of artificial agents but remains a fragmented field: diverse theories, terminologies, and design choices have led to disjointed developments and limited comparability across systems. Existing overviews remain at a conceptual level that is undiscerning to the underlying algorithms, representations, and their respective success. Methods: We address this gap by performing an explorative systematic review. Reports were included if they described techniques enabling Computational Metacognitive Architectures (CMAs) to model, store, remember, and process their episodic metacognitive experiences, one of Flavell's (1979a) three foundational components of metacognition. Searches were conducted in 16 databases, consulted between December 2023 and June 2024. Data were extracted using a 20-item framework considering pertinent aspects. Results: A total of 101 reports on 35 distinct CMAs were included. Our findings show that metacognitive experiences may boost system performance and explainability, e.g., via self-repair. However, lack of standardization and limited evaluations may hinder progress: only 17% of CMAs were quantitatively evaluated regarding this review's focus, and significant terminological inconsistency limits cross-architecture synthesis. Systems also varied widely in memory content, data types, and employed algorithms. Discussion: Limitations include the non-iterative nature of the search query, heterogeneous data availability, and an under-representation of emergent, sub-symbolic CMAs. Future research should focus on standardization and evaluation, e.g., via community-driven challenges, and on transferring promising principles to emergent architectures. |
| title | How Metacognitive Architectures Remember Their Own Thoughts: A Systematic Review |
| topic | Neurons and Cognition Artificial Intelligence I.2.0; I.2.4; I.2.6; I.2.8; J.4 |
| url | https://arxiv.org/abs/2503.13467 |