Cognitive Architectures for Tomorrow: A Comprehensive Survey of Memory Management Paradigms in Agentic AI Systems

Cognitive Architectures for Tomorrow: A Comprehensive Survey of Memory Management Paradigms in Agentic AI Systems | 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 Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed.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. 13 August 2025 V1 Latest version Share on Cognitive Architectures for Tomorrow: A Comprehensive Survey of Memory Management Paradigms in Agentic AI Systems Authors : Surya Rao Rayarao 0009-0001-8467-7865 [email protected] and Naga Donikena Authors Info & Affiliations https://doi.org/10.22541/au.175510732.22202636/v1 774 views 309 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract As artificial intelligence systems evolve from simple query-response models to sophisticated agentic architectures capable of complex reasoning and autonomous decision-making, the management of memory becomes increasingly critical. This comprehensive survey examines the landscape of memory management in agentic AI systems, drawing parallels between human cognitive processes and artificial memory architectures. We explore the fundamental dichotomy between short-term context windows and long-term conversational memory, analyze the distinctions between episodic and semantic memory systems, and investigate the challenges inherent in implementing effective memory management for AI agents. Our analysis encompasses retrieval-augmented generation (RAG) methodologies, including lexical, vector, hybrid, and agentic approaches, while examining core memory management components such as initialization, segmentation, structure creation, retrieval, updating, and deletion. We provide detailed examinations of cutting-edge memory architectures including Generative Agents, A-Mem, MemGPT, and agent workflow memory systems. Additionally, we explore the emerging concept of memory providers and their architectural implications for AI applications. This survey aims to provide researchers and practitioners with a comprehensive understanding of current memory management paradigms and their practical implementations in agentic systems. Supplementary Material File (agentic_ai_memory_management_paradigms.pdf) Download 139.42 KB Information & Authors Information Version history V1 Version 1 13 August 2025 Copyright This work is licensed under a Non Exclusive No Reuse License. Keywords agentic systems artificial intelligence cognitive architectures conversational ai episodic memory memory management retrieval-augmented generation semantic memory Authors Affiliations Surya Rao Rayarao 0009-0001-8467-7865 [email protected] Department of Statistics and Data Sciences Department of Computer Science, The University of Texas at Austin Austin View all articles by this author Naga Donikena Department of Statistics and Data Sciences Department of Computer Science, The University of Texas at Austin Austin View all articles by this author Metrics & Citations Metrics Article Usage 774 views 309 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Surya Rao Rayarao, Naga Donikena. Cognitive Architectures for Tomorrow: A Comprehensive Survey of Memory Management Paradigms in Agentic AI Systems. Authorea . 13 August 2025. DOI: https://doi.org/10.22541/au.175510732.22202636/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.175510732.22202636/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:'9ffdfe33ff8cc13d',t:'MTc3OTQ3NTY4NA=='};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())}}}})();