Composable Modular Intelligence: A Memory-Centric Modular AI Architecture for Adaptive Cognitive Systems

This paper introduced a novel Composable Modular Intelligence framework that redefines intelligence as the coordinated interaction among modular cognitive systems. The architecture combines independently deployable micro-models, orchestration-based reasoning, and a multi-layer adaptive memory system. This framework addresses the limitations of traditional AI architectures by allowing for real-time flexibility, memory-driven adaptation, and personalized cognitive growth. Future work will focus on real-world deployment, optimizing distributed orchestration, and integrating multimodal reasoning systems. 

[1] W. Cai et al., "A Survey on Mixture of Experts in Large Language Models," IEEE Transactions on Knowledge and Data Engineering, 2025.  [2] "Parameter-Efficient Fine-Tuning in Large Language Models," Artificial Intelligence Review, Springer, 2025.  [3] "Parameter-Efficient Fine-Tuning of Large Language Models Using Semantic Knowledge Tuning," Scientific Reports, vol. 14, Art. no. 27890, 2024.  [4] J. Wu et al., "Omni-Smola: Boosting Generalist Multimodal Models with Soft Mixture of Low-Rank Experts," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 14205–14215.  [5] S. Mu and S. Lin, "A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications," arXiv preprint arXiv:2503.07137, 2025.  [6] R. Hwang et al., "Pre-Gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference," in Proceedings of the ACM/IEEE International Symposium on Computer Architecture (ISCA), 2024.  [7] D. Li et al., "MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-Based Mixture of Experts," arXiv preprint arXiv:2404.15159, 2024.  [8] W. Fedus, B. Zoph, and N. Shazeer, "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity," Journal of Machine Learning Research, vol. 23, no. 120, pp. 1–39, 2022.  [9] E. J. Hu et al., "LoRA: Low-Rank Adaptation of Large Language Models," in Proceedings of the International Conference on Learning Representations (ICLR), 2022.  [10] N. Shazeer et al., "Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer," in Proceedings of the International Conference on Learning Representations (ICLR), 2017.