Multi-Agent AI Systems for Detecting Emerging Therapeutic Targets and Intervention Patterns in Neuroplasticity Research
Article Sidebar
Main Article Content
Abstract
The exponential growth of neuroplasticity research presents profound challenges to the manual synthesis of literature, hindering the identification of emerging therapeutic targets and intervention patterns. While multi-agent Artificial Intelligence (AI) systems have been proposed conceptually to address this, concrete implementations demonstrating end-to-end utility are scarce. This paper details the successful implementation and application of a novel four-agent AI system designed to automate the discovery, extraction, analysis, and validation of patterns in neuroplasticity literature. Our platform consists of four parts: a Literature Discovery Agent (LDA) for corpus gathering, a Concept Extraction Agent (CEA) with a multi-level NLP strategy fallback mechanism for improving resilience, a Pattern Analysis Agent (PAA) utilizing machine learning for thematic grouping and trend analysis, and a Validation Agent (VA) purely for the validation phase. The authors have a specific case study on neuroplasticity with respect to stroke rehabilitation research, where the platform automatically processed 533 scientific papers, extracted 4,393 biomedical entities, and isolated four research sub-fields that are not only statistically significant but also relevant to the topic: (1) Vagus Nerve Stimulation, (2) Molecular and Synaptic Processes involving Brain-Derived Neurotrophic Factor (BDNF), Clinical and Music Therapies, and finally (3) Brain-Computer Interface and Motor Training. This research project illustrates the efficacy and utilization capacity of collective AI validation beyond any purely conceptual framework.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published in JIWE are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License. Readers are allowed to
- Share — copy and redistribute the material in any medium or format under the following conditions:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use;
- NonCommercial — You may not use the material for commercial purposes;
- NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.
References
L. B. Ezzdine et al., “Physical activity and neuroplasticity in neurodegenerative disorders: A comprehensive review of exercise interventions, cognitive training, and AI applications,” Frontiers in Neuroscience, vol. 19, pp. 1502417, 2025, doi: 10.3389/fnins.2025.1502417.
R. Onciul et al., “Artificial Intelligence and neuroscience: Transformative synergies in brain research and clinical applications,” Journal of Clinical Medicine, vol. 14, no. 2, pp. 550, 2025, doi: 10.3390/jcm14020550.
S. Sadegh-Zadeh, M. Bahrami, O. Soleimani, and S. Ahmadi, "Neural reshaping: The plasticity of human brain and artificial intelligence in the learning process," American Journal of Neurodegenerative Disease, vol. 13, no. 5, pp. 34-48, 2024, doi: 10.62347/nhkd7661.
R. van Dinter, B. Tekinerdogan, and C. Catal, "Automation of systematic literature reviews: A systematic literature review," Information and software technology, vol. 136, pp. 106589, Aug 2021, doi: 10.1016/j.infsof.2021.106589.
T. Rudroff, O. Rainio, and R. Klen, “Neuroplasticity meets Artificial Intelligence: A hippocampus-inspired approach to the stability–plasticity dilemma,” Brain Sciences, vol. 14, no. 11, pp. 1111, 2024, doi: 10.3390/brainsci14111111.
F. Tian et al., “An outlook on the opportunities and challenges of multi-agent AI systems,” arXiv preprint, 2025, doi: https://doi.org/10.48550/arXiv.2505.18397.
T. Guo et al., “Large language model based multi-agents: A survey of progress and challenges,” arXiv preprint, 2025, doi: 10.48550/arXiv.2402.01680.
S. Liu, Z. Liang, X. Lyu, and C. Amato, “LLM collaboration with multi-agent reinforcement learning,” in Proceeding AAAI Technical Track on Natural Language Processing III, vol. 40, Mar. 2026, doi: 10.1609/aaai.v40i38.40487
S. Gao et al. , “Empowering biomedical discovery with AI agents,” Cell, vol. 187, no. 22, pp. 6125–6151, Oct 31, 2024, doi: 10.1016/j.cell.2024.09.022.
P.H. Luzolo, Z. Elrawashdeh, I. Tchappi, S. Galland, and F. Outay, “Combining multi-agent systems and artificial intelligence of things: Technical challenges and gains,” Internet of things (Amsterdam. Online), vol. 28, pp. 101364, Dec. 2024, doi: 10.1016/j.iot.2024.101364.
A.M. Sami et al., “System for systematic literature review using multiple AI agents: Concept and an empirical evaluation,” arXiv preprint, 2025, doi: 10.48550/arXiv.2403.08399.
A. Calderone et al., “Towards transforming neurorehabilitation: The impact of Artificial Intelligence on diagnosis and treatment of neurological disorders,” Biomedicines, vol. 12, no. 10, pp. 2415, 2024, doi: 10.3390/biomedicines12102415.
L. Chen et al., “AI agent behavioral science,” arXiv preprint, 2025, doi: 10.48550/arXiv.2506.06366.
I. D. S. Portugal, P. Alencar, and D. Cowan, “An Agentic AI-based multi-agent framework for recommender systems,” 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA, pp. 5375-5382, 2024 doi: 10.1109/BigData62323.2024.10825765.
E. Shakshuki, and M. Reid, "Multi-agent system applications in healthcare: Current technology and future roadmap," Procedia Computer Science, vol. 52, pp. 252–261, 2015, doi: 10.1016/j.procs.2015.05.071.
D. Kosaraju, “AI and multi-agent systems: Collaboration and competition in autonomous environments,” International Journal of Research and Review, vol. 10, no. 12, pp. 883–888, Nov 30. 2024, doi: 10.52403/ijrr.20231288.
D. Maldonado, E. Cruz, J. Abad Torres, P. J. Cruz, and S. d. P. Gamboa Benitez, “Multi-agent systems: A survey about its components, framework and workflow,” in IEEE Access, vol. 12, pp. 80950-80975, 2024, doi: 10.1109/ACCESS.2024.3409051.
M. Falco, and G. Robiolo, "A systematic literature review in multi-agent systems: Patterns and trends," 2019 XLV Latin American Computing Conference (CLEI), Panama, pp. 1-10, 2019, doi: 10.1109/CLEI47609.2019.235098.
P. Balaji, and D. Srinivasan, “An introduction to multi-agent systems,” Studies in Computational Intelligence, pp. 1–27, 2010, doi: 10.1007/978-3-642-14435-6_1.
A. Bandi, B. Kongari, R. Naguru, S. Pasnoor, and S. V. Vilipala, “The rise of agentic AI: A review of definitions, frameworks, architectures, applications, evaluation metrics, and challenges,” Future Internet, vol. 17, no. 9, pp. 404, 2025, doi: 10.3390/fi17090404.
D. Wu et al., “Generative multi-agent collaboration in embodied AI: A systematic review,” arXiv preprint, 2025, doi: 10.48550/arXiv.2502.11518.
D. Grossi, A. Rosenfeld, and N. Talmon, “Advances in multi-agent systems research: EUMAS 2021 Extended selected papers,” Sn Computer Science, vol. 4, no. 5, 2023, doi: 10.1007/s42979-023-02098-0.
R. Calegari, G. Ciatto, V. Mascardi, and A. Omicini, “Logic-based technologies for multi-agent systems: A systematic literature review,” Autonomous Agents and Multi-Agent Systems, vol. 35, no. 1, 2020, doi: 10.1007/s10458-020-09478-3.
X. Li, S. Wang, S. Zeng, Y. Wu, and Y. Yang, “A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges,” Vicinagearth, vol. 1, no. 1, 2024, doi: 10.1007/s44336-024-00009-2.
Ebadi, A. Auger, and Y. Gauthier, “Detecting emerging technologies and their evolution using deep learning and weak signal analysis,” Journal of Informetrics, vol. 16, no. 4, pp. 101344, Nov 1. 2022, doi: 10.1016/j.joi.2022.101344.
E. Pretel, A. Moya, E. Navarro, V. Lopez-Jaquero, and P. Gonzalez, “Analysing the synergies between multi-agent systems and digital twins: A systematic literature review," Information and Software Technology, vol. 174, pp. 107503, Oct. 2024, doi: 10.1016/j.infsof.2024.107503.
Y. Gao et al., “Vagus nerve stimulation paired with rehabilitation for motor function, mental health and activities of daily living after stroke: A systematic review and meta-analysis,” Journal of Neurology Neurosurgery & Psychiatry, vol. 94, no. 4, pp. 257–266, 2022, doi: 10.1136/jnnp-2022-329275.
J. A. Ramos-Castaneda, C. F. Barreto-Cortes, D. Losada-Floriano, S. M. Sanabria-Barrera, F. A. Silva-Sieger, and R. G. Garcia, "Efficacy and safety of vagus nerve stimulation on upper limb motor recovery after stroke. A systematic review and meta-analysis," Frontiers in Neurology, vol. 13, 2022, doi: 10.3389/fneur.2022.889953.
X. Wang et al., “Application of vagus nerve stimulation on the rehabilitation of upper limb dysfunction after stroke: A systematic review and meta-analysis,” Frontiers in Neurology, vol. 14, 2023, doi: 10.3389/fneur.2023.1189034.
H. Park, and M. Poo, “Neurotrophin regulation of neural circuit development and function,” Nature Reviews Neuroscience, vol. 14, no. 1, pp. 7–23, 2012, doi: 10.1038/nrn3379.
G. Leal, C. R. Bramham, and C. B. Duarte, “BDNF and hippocampal synaptic plasticity,” Vitamins and Hormones, pp. 153–195, 2017, doi: 10.1016/bs.vh.2016.10.004.
M. A. Cervera et al., "Brain-computer interfaces for post-stroke motor rehabilitation: a meta-analysis," Annals of Clinical and Translational Neurology, vol. 5, no. 5, pp. 651-663, 2018, doi: 10.1002/acn3.544.
L. Zhang, M. Zhang, Y. Zhang, N. Li, J. Hu, and X. Peng, “Efficacy of brain–computer interface with functional electrical stimulation, transcranial direct current stimulation, and conventional therapy on upper limb recovery after stroke: A systematic review and network meta-analysis,” Frontiers in Neurology, vol. 16, Art. no. 1643536, 2025, doi: 10.3389/fneur.2025.1643536.
S. Palaniappan, R. Logeswaran, K. Subaramaniam, O. Baker, and B. Ngoc Dung, “Training the brain: A machine learning approach to predicting wellbeing through intentional thought pattern modification”, Journal of Informatics and Web Engineering, vol. 4, no. 3, pp. 64–89, Oct. 2025, doi: 10.33093/jiwe.2025.4.3.4.
S. Palaniappan, R. Logeswaran, and Y. L. Yong, “Machine learning model for assessing human well-being using brain wave activities”, Journal of Informatics and Web Engineering, vol. 4, no. 2, pp. 93–113, Jun. 2025, doi: 10.33093/jiwe.2025.4.2.7.