Thinking Machines: A Dual-System Framework for Metacognitive Control and Learning

Thinking Machines: A Dual-System Framework for Metacognitive Control and Learning | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 6 March 2026 V1 Latest version Share on Thinking Machines: A Dual-System Framework for Metacognitive Control and Learning Authors : Ananta Nair 0009-0006-6878-486X [email protected] , Erin E Austin , Jason M Watson , and Farnoush Banaei-Kashani Authors Info & Affiliations https://doi.org/10.22541/au.177282011.14079783/v1 203 views 83 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract A foundational challenge for artificial intelligence is not whether machines can solve welldefined tasks, but whether they can adapt across novel and open-ended domains. Biological systems achieve such adaptivity by coupling fast sensorimotor control with slower abstraction and memory consolidation across timescales. Despite remarkable progress, contemporary large-scale models remain energy-inefficient at inference, weakly coupled to embodied goal-directed control, and prone to interference without principled consolidation. We propose a dual-loop architecture that couples a fast recurrent perception-action loop with a slow consolidation-and-planning loop that reorganizes experience into compositional memories over a learned relational graph. The fast loop is implemented as a stable excitatory-inhibitory dynamical system with online prediction-error learning, uncertaintyaware state estimation, and asymmetric consequence-driven updating in which aversive outcomes produce rapid, preferential policy correction and memory consolidation. The slow loop performs attention-based associative retrieval over a spectrally structured memory graph, enabling context-sensitive diffusion-based recall and the composition of long-horizon plans from consolidated fragments. Both loops share a common dynamical substrate and are derived from a single variational objective that unifies learning, action selection, and uncertainty estimation via free energy minimization, enabling metacognitive regulation of computational depth by scaling inference resources to predictive uncertainty. We prove Lyapunov stability for the fast-loop dynamics under quasi-static learning assumptions and establish robustness bounds for inter-loop coupling under timescale separation. The framework yields four falsifiable predictions: improved task switching, reduced catastrophic forgetting, compositional zero-shot transfer, and uncertainty-adaptive compute allocation, providing concrete criteria for evaluation in embodied control, continual learning, and compositional generalization. Supplementary Material File (thinking machine 2.pdf) Download 745.33 KB Information & Authors Information Version history V1 Version 1 06 March 2026 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords active inference artificial intellgence dual-loop architecture free energy minimization kalman filtering lyapunov stability metacognitive control modern hopfield networks multi-timescale consolidation spectral graph organization temporal difference learning Authors Affiliations Ananta Nair 0009-0006-6878-486X [email protected] Dell Technologies View all articles by this author Erin E Austin University of Colorado Denver View all articles by this author Jason M Watson University of Colorado Denver View all articles by this author Farnoush Banaei-Kashani University of Colorado Denver View all articles by this author Metrics & Citations Metrics Article Usage 203 views 83 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Ananta Nair, Erin E Austin, Jason M Watson, et al. Thinking Machines: A Dual-System Framework for Metacognitive Control and Learning. Authorea . 06 March 2026. DOI: https://doi.org/10.22541/au.177282011.14079783/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.177282011.14079783/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fdf97058d9e41e2',t:'MTc3OTE1Njg4NQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();