{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:00:24Z","timestamp":1762192824052,"version":"build-2065373602"},"reference-count":33,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Athabasca University\u2019s Academic Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Achieving Artificial General Intelligence (AGI) requires a unified framework capable of modeling the full spectrum of intelligent behavior\u2014from logical reasoning and sensory perception to emotional regulation and collective decision-making. This paper proposes Constrained Object Hierarchies (COH), a neuroscience-inspired theoretical model that represents intelligent systems as hierarchical compositions of objects governed by symbolic structure, neural adaptation, and constraint-based control. Each object is formally defined by a 9-tuple structure: O=(C,A,M,N,E,I,T,G,D), encapsulating its Components, Attributes, Methods, Neural components, Embedding, and governing Identity constraints, Trigger constraints, Goal constraints, and Constraint Daemons. To demonstrate the scope and versatility of COH, we formalize nine distinct intelligence types\u2014including computational, perceptual, motor, affective, and embodied intelligence\u2014each with detailed COH parameters and implementation blueprints. To operationalize the framework, we introduce GISMOL, a Python-based toolkit for instantiating COH objects and executing their constraint systems and neural components. GISMOL supports modular development and integration of intelligent agents, enabling a structured methodology for AGI system design. By unifying symbolic and connectionist paradigms within a constraint-governed architecture, COH provides a scalable and explainable foundation for building general purpose intelligent systems. A comprehensive summary of the research contributions is presented right after the introduction.<\/jats:p>","DOI":"10.3390\/computers14110478","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T17:32:01Z","timestamp":1762191121000},"page":"478","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Constrained Object Hierarchies as a Unified Theoretical Model for Intelligence and Intelligent Systems"],"prefix":"10.3390","volume":"14","author":[{"given":"Harris","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computing and Information Systems, Athabasca University, Athabasca, AB T9S 3A3, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,3]]},"reference":[{"key":"ref_1","unstructured":"Xiong, H., Wang, Z., Li, X., Bian, J., Xie, Z., Mumtaz, S., Al-Dulaimi, A., and Barnes, L.E. (2024). Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents. arXiv, Available online: https:\/\/arxiv.org\/pdf\/2407.08516."},{"key":"ref_2","first-page":"1","article-title":"A Hybrid Cognitive Architecture for AGI: Bridging Symbolic and Subsymbolic AI","volume":"2","author":"Hans","year":"2025","journal-title":"Int. J. Futur. Multidiscip. Res."},{"key":"ref_3","unstructured":"Laird, J.E. (2022). Introduction to Soar. arXiv, Available online: https:\/\/arxiv.org\/abs\/2205.03854."},{"key":"ref_4","unstructured":"Stocco, A., Mitsopoulos, K., Yang, Y.C., Hake, H.S., Haile, T., Leonard, B., and Gluck, K. (2024). Fitting, Evaluating, and Comparing Cognitive Architecture Models Using Likelihood: A Primer with Examples in ACT-R. arXiv, Available online: https:\/\/arxiv.org\/abs\/2410.18055."},{"key":"ref_5","unstructured":"Sun, R. (2025). Enhancing Computational Cognitive Architectures with LLMs: A Case Study. arXiv, Available online: https:\/\/arxiv.org\/abs\/2509.10972."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.cogsys.2017.05.001","article-title":"The Knowledge Level in Cognitive Architectures: Current Limitations and Possible Developments","volume":"48","author":"Lieto","year":"2018","journal-title":"Cogn. Syst. Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2500","DOI":"10.1038\/s41593-024-01787-0","article-title":"Integrating Brainstem and Cortical Functional Architectures","volume":"27","author":"Hansen","year":"2024","journal-title":"Nat. Neurosci."},{"key":"ref_8","unstructured":"Zhong, J., Feng, L., Jin, H., and Chen, K. (2025). Advances in deep learning for perception science: Modeling mechanisms and applications. Front. Psychol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2024.3471571","article-title":"Towards Data-and Knowledge-Driven AI: A Survey on Neuro-Symbolic Computing","volume":"47","author":"Wang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","unstructured":"Cohen, W.W. (2016). TensorLog: A Differentiable Deductive Database. arXiv, Available online: https:\/\/arxiv.org\/abs\/1605.06523."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nigro, L., and Cicirelli, F. (2024). Formal Modeling and Verification of Embedded Real-Time Systems: An Approach and Practical Tool Based on Constraint Time Petri Nets. Mathematics, 12, Available online: https:\/\/www.mdpi.com\/2227-7390\/12\/6\/812.","DOI":"10.3390\/math12060812"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zagha, E. (2020). Shaping the Cortical Landscape: Functions and Mechanisms of Top-Down Cortical Feedback Pathways. Front. Syst. Neurosci., 14, Available online: https:\/\/www.frontiersin.org\/articles\/10.3389\/fnsys.2020.00033\/full.","DOI":"10.3389\/fnsys.2020.00033"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Curtis, C.E., and Sprague, T.C. (2021). Persistent Activity During Working Memory From Front to Back. Front. Neural. Circuits, 15, Available online: https:\/\/www.frontiersin.org\/articles\/10.3389\/fncir.2021.696060\/full.","DOI":"10.3389\/fncir.2021.696060"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Masselink, J., and Lappe, M. (2025). Adaptation Across the 2D Population Code Explains the Spatially Distributive Nature of Motor Learning. PLoS Comput. Biol., 21.","DOI":"10.1371\/journal.pcbi.1013041"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Temudo, A., Dolfen, N., King, B.R., and Albouy, G. (2025). The Human Medial Temporal Lobe Represents Memory Items in Their Ordinal Position in Both Declarative and Motor Memory Domains. PLoS Biol., 23.","DOI":"10.1371\/journal.pbio.3003267"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jiang, L.P., and Rao, R.P.N. (2023). Predictive Coding Theories of Cortical Function. Oxford Research Encyclopedia of Neuroscience, Oxford University Press. Available online: https:\/\/arxiv.org\/abs\/2112.10048.","DOI":"10.1093\/acrefore\/9780190264086.013.328"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1038\/s42256-024-00863-1","article-title":"Automated Construction of Cognitive Maps with Visual Predictive Coding","volume":"6","author":"Gornet","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"119021","DOI":"10.1016\/j.neuroimage.2022.119021","article-title":"The Role of Ventral Stream Areas for Viewpoint-Invariant Object Recognition","volume":"251","author":"Nestmann","year":"2022","journal-title":"NeuroImage"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e1436242025","DOI":"10.1523\/JNEUROSCI.1436-24.2025","article-title":"Understanding Human Amygdala Function with Artificial Neural Networks","volume":"45","author":"Jang","year":"2025","journal-title":"J. Neurosci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"bhaf092","DOI":"10.1093\/cercor\/bhaf092","article-title":"Functional Connectivity Between the Right Rostral Anterior Cingulate Cortex and the Right Dorsolateral Prefrontal Cortex Underlies the Association Between Future Self-Continuity and Self-Control","volume":"35","author":"Huang","year":"2025","journal-title":"Cereb. Cortex"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Kirschenhofer, T., Harvey, M., and Rainer, G. (2024). Mediodorsal Thalamus and Ventral Pallidum Contribute to Subcortical Regulation of the Default Mode Network. Commun. Biol., 7, Available online: https:\/\/www.nature.com\/articles\/s42003-024-06531-9.pdf.","DOI":"10.1038\/s42003-024-06531-9"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Molina, D., Poyatos, J., Del Ser, J., Garc\u00eda, S., Hussain, A., and Herrera, F. (2024). Comprehensive Taxonomies of Nature- and Bio-Inspired Optimization: Inspiration Versus Algorithmic Behavior, Critical Analysis and Recommendations (2020\u20132024). arXiv, Available online: https:\/\/arxiv.org\/html\/2002.08136v5.","DOI":"10.1007\/s12559-020-09730-8"},{"key":"ref_23","unstructured":"Agrawal, P., Tan, C., and Rathore, H. (2023). Advancing Perception in Artificial Intelligence through Principles of Cognitive Science. arXiv, Available online: https:\/\/arxiv.org\/pdf\/2310.08803."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"adw7660","DOI":"10.1126\/scirobotics.adw7660","article-title":"Physical Control: A New Avenue to Achieve Intelligence in Soft Robotics","volume":"10","author":"Milana","year":"2025","journal-title":"Sci. Robot."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s41235-024-00578-2","article-title":"Evidence-Based Scientific Thinking and Decision-Making in Everyday Life","volume":"9","author":"Dawson","year":"2024","journal-title":"Cogn. Res. Princ. Implic."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ma, F., Yuan, Y., Xie, Y., Ren, H., Liu, I., He, Y., Ren, F., Yu, F.R., and Ni, S. (2024). Generative Technology for Human Emotion Recognition: A Scope Review. arXiv, Available online: https:\/\/arxiv.org\/abs\/2407.03640.","DOI":"10.2139\/ssrn.4889990"},{"key":"ref_27","unstructured":"Cui, H., and Yasseri, T. (2024). AI-Enhanced Collective Intelligence: The State of the Art and Prospects. arXiv, Available online: https:\/\/arxiv.org\/html\/2403.10433v1."},{"key":"ref_28","first-page":"45","article-title":"Understanding Artificial General Intelligence: Defining Characteristics and Benchmarks","volume":"2","author":"Muhsen","year":"2025","journal-title":"J. Artif. Intell. Control Syst."},{"key":"ref_29","unstructured":"Rahman, M.A.U., and Schranz, M. (2025). LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?. arXiv, Available online: https:\/\/arxiv.org\/pdf\/2506.14496."},{"key":"ref_30","unstructured":"Long, X., Zhao, Q., Zhang, K., Zhang, Z., Wang, D., Liu, Y., Shu, Z., Lu, Y., Wang, S., and Wei, X. (2025). A Survey: Learning Embodied Intelligence from Physical Simulators and World Models. arXiv, Available online: https:\/\/arxiv.org\/abs\/2507.00917."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/nrn2787","article-title":"The free-energy principle: A unified brain theory?","volume":"11","author":"Friston","year":"2010","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_32","first-page":"1234","article-title":"Aligning crowd-sourced human feedback for reinforcement learning on code generation by large language models","volume":"10","author":"Wong","year":"2024","journal-title":"IEEE Trans. Big Data"},{"key":"ref_33","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., and Ray, A. (2022). Training language models to follow instructions with human feedback. arXiv."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/478\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T17:47:38Z","timestamp":1762192058000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/11\/478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":33,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["computers14110478"],"URL":"https:\/\/doi.org\/10.3390\/computers14110478","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,3]]}}}