Keywords
Retrieval-Augmented Generation (RAG)
Agentic AI Architectures
Cognitive Control in Artificial Intelligence
AI Governance and Stewardship
How to Cite
Abstract
As large language model systems evolve from standalone text generators into retrieval-enabled, tool-using, and multi-session agents, researchers increasingly turn to cognitiveneuroscience for interpretive guidance. This paper argues that such comparisons areuseful only when they are bounded, functionally specified, and empirically falsifiable. Weanalyze retrieval-augmented generation as a separation between parametric knowledgeand external evidence access, and we analyze agent runtimes as control layers responsiblefor planning, routing, tool use, and context management. We distinguish these runtimefunctions from Model Context Protocol, which is an interoperability standard for exposingresources, prompts, and tools rather than a theory of memory or executive control. On thisbasis, we propose the RCS Triad Retrieval, Control, and Stewardship as a compactframework for describing modern LLM systems. Retrieval concerns evidence access andmemory extension; Control concerns orchestration, tool selection, and active context;Stewardship concerns provenance, consent, auditability, risk boundaries, and humanoversight. The paper’s central claim is methodological rather than biological: neuroscienceshould not be used to assert one-to-one equivalence between brains and models, but togenerate disciplined architectural hypotheses. We position the RCS Triad against eightadjacent retrieval and agent frameworks in a comparative table, specify its boundaryconditions through a Convergence-Divergence Matrix across eight cognitive domains,and outline a benchmarkable empirical agenda with four falsifiable predictions. We alsointroduce two original governance concepts architectural negligence and goaltransparency as frameworks for understanding the liability and rights questions thatarise when AI systems confabulate and persist goal-states.
References
1. Baars, B. J. (1988). A cognitive theory of consciousness. Cambridge Univ Press.
2. Baddeley, A. D., & Hitch, G. J. (1974). Working memory. In G. A. Bower (Ed.), Thepsychology of learning and motivation (Vol. 8, pp. 47–89). Academic Press.
3. Dehaene, S., Changeux, J.-P., & Dehaene-Lambertz, G. (2011). Experimental andtheoretical approaches to conscious processing. Neuron, 70(2), 200–227.https://doi.org/10.1016/j.neuron.2011.03.018• Dennett, D. C. (1987). The intentional stance. MIT Press.• Feinberg, J. (1974). The rights of animals & unborn generations. In W. T. Blackstone (Ed.),Philosophy & environmental crisis (pp. 43–68). Univ of Georgia Press.• Fodor, J. A. (1983). The modularity of mind. MIT Press.• Friston, K. (2010). The free-energy principle: A unified brain theory? Nature ReviewsNeuroscience, 11(2), 127–138. https://doi.org/10.1038/nrn2787• Kahneman, D. (2011). Thinking, fast and slow. Farrar, Straus and Giroux.• Lakoff, G., & Johnson, M. (1999). Philosophy in the flesh: The embodied mind and itschallenge to Western thought. Basic Books.• McClelland, J. L., McNaughton, B. L., & O'Reilly, R. C. (1995). Why there arecomplementary learning systems in the hippocampus and neocortex. PsychologicalReview, 102(3), 419–457. https://doi.org/10.1037/0033-295X.102.3.419• Lewis, P., et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLPTasks.• Nielsen, J. A., et al. (2013). An Evaluation of the Left-Brain vs. Right-Brain Hypothesis withResting State Functional Connectivity MRI.• Yao, S., et al. (2023). ReAct: Synergizing Reasoning and Acting in Language Models.• Asai, A., et al. (2024). Self-RAG: Learning to Retrieve, Generate, and Critique throughSelf-Reflection.• Gao, T., et al. (2023). Enabling Large Language Models to Generate Text with Citations.• Anderson, J. R. (2014). Rules of the Mind. Psychology Press.• Zhong, W., et al. (2024 / 2023 preprint). MemoryBank: Enhancing Large Language Modelswith Long-Term Memory.• Park, J. S., et al. (2023). Generative Agents: Interactive Simulacra of Human Behavior.• Baddeley, A. D. (2000). The episodic buffer: A new component of working memory? Trendsin Cognitive Sciences, 4(11), 417–423. https://doi.org/10.1016/S1364-6613(00)01538-2• Badre, D., & D'Esposito, M. (2009). Is the rostro-caudal axis of the frontal lobehierarchical? Nature Reviews Neuroscience, 10(9), 659–669.https://doi.org/10.1038/nrn2667• Cowan, N. (2001). The magical number 4 in short-term memory: A reconsideration ofmental storage capacity. Behavioral and Brain Sciences, 24(1), 87–114.• Floridi, L. (2011). The Philosophy of Information. Oxford University Press.• Garcez, A. d., Besold, T. R., De Raedt, L., Földiak, P., Hitzler, P., Icard, T., ... & Silver, D.L. (2019). Neural-symbolic learning and reasoning: A survey & interpretation.© Dr Lalith Kumar Vemali; Dr Rakesh GandlaPhilosophical Transactions of the Royal Society A: Mathematical, Physical & EngineeringSciences, 377(2152), 20180070. https://doi.org/10.1098/rsta.2018.0070• Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017). Neuroscience-Inspired Artificial Intelligence. Neuron, 95(2), 245–258.https://doi.org/10.1016/j.neuron.2017.06.011• Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., ... & Zhang, Y. (2023). Hallucination inNatural Language Generation: A Survey. ACM Computing Surveys (CSUR), 55(12), 1–38.• Popper, K. R. (1959). The logic of scientific discovery. Hutchinson. (Original workpublished 1934 as Logik der Forschung)• Fuster, J. M. (2001). The prefrontal cortex — an update: Time is of the essence. Neuron,30(2), 319–333.• Graves, A., Wayne, G., & Danihelka, I. (2014). Neural Turing machines. arXiv:1410.5401• Stanovich, K. E., & West, R. F. (2000). Individual differences in reasoning: Implications forthe rationality debate. Behavioral and Brain Sciences, 23(5), 645–665.• Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., ... & Yih, W. T. (2020).Dense Passage Retrieval for Open-Domain Question Answering. Proceedings of the 2020Conference on Empirical Methods in Natural Language Processing (EMNLP), 6769–6781.https://doi.org/10.18653/v1/2020.emnlp-main.550• Kriegeskorte, N., & Douglas, P. K. (2018). Cognitive computational neuroscience. NatureNeuroscience, 21(9), 1148–1160. https://doi.org/10.1038/s41593-018-0210-5• Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., ... & Riedel, S. (2020).Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances inNeural Information Processing Systems, 33, 9459–9474.• Lipton, Z. C. (2018). The mythos of model interpretability. Communications of the ACM,61(10), 36–43. https://doi.org/10.1145/3233231• Madotto, A., Lin, Z., Wu, C. S., & Fung, P. (2020). The Copy-Paste Transformer: SimpleCopy Mechanism for Faster Training and Inference. arXiv preprint arXiv:2005.10510.https://arxiv.org/abs/2005.10510• McGaugh, J. L. (2004). The amygdala modulates the consolidation of memories ofemotionally arousing experiences. Annual Review of Neuroscience, 27, 1–28.https://doi.org/10.1146/annurev.neuro.27.070203.144157• Miller, E. K., & Cohen, J. D. (2001). An integrative theory of prefrontal cortex function.Annual Review of Neuroscience, 24, 167–202.https://doi.org/10.1146/annurev.neuro.24.1.167• Miller, G. A. (1956). The magical number seven, plus or minus two: Some limits on ourcapacity for processing information. Psychological Review, 63(2), 81–97.https://doi.org/10.1037/h0043158• Pessoa, L. (2008). On the relationship between emotion and cognition. Nature ReviewsNeuroscience, 9(2), 148–158. https://doi.org/10.1038/nrn2317
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Journal of Cortexplore