Automated Database Schema Matching Using Agentic Large Language Models and Semantic Similarity

Main Article Content

Ms. Anamika Soni

Abstract

Automated database schema matching is an essential process for integrating heterogeneous databases and enabling consistent data exchange across diverse information systems. Traditional schema matching techniques rely on linguistic, structural, instance-based, and machine learning (ML) approaches, but they often struggle with inconsistent naming conventions, domain-specific terminology, complex relationships, and evolving data structures. New developments in large-scale language models allow for better semantic reasoning and contextual comprehension, which in turn improves the ability to find relationships between database attributes. However, standalone models may produce inconsistent predictions and require additional validation for reliable matching. This paper reviews automated database schema matching using agentic large language models and semantic similarity techniques. It examines fundamental schema matching methods, semantic similarity approaches, automation strategies, and agentic reasoning capabilities, including planning, search, and tool utilization. Existing frameworks, including LLM-Matcher and Matchmaker, are discussed alongside machine learning, multimodal fusion, and explainable matching approaches. The review identifies research gaps in autonomous decision-making, iterative validation, scalability, explainability, and reduced human intervention. Finally, it highlights the need for an integrated framework combining agentic reasoning and semantic similarity to achieve accurate, adaptive, transparent, and efficient schema matching across heterogeneous database environments.

Downloads

Download data is not yet available.

Article Details

Section

Research Paper

Author Biography

Ms. Anamika Soni, Mandsaur University, Mandsaur


Assistant Professor
Department of Computer Sciences and Applications

How to Cite

Automated Database Schema Matching Using Agentic Large Language Models and Semantic Similarity (M. A. . Soni , Trans.). (2026). Journal of Global Research in Multidisciplinary Studies(JGRMS), 2(10), 16-21. https://doi.org/10.67805/jgrms.v2i10.159

References

[1] M. Parciak, B. Vandevoort, F. Neven, L. M. Peeters, and S. Vansummeren, “Schema Matching with Large Language Models: an Experimental Study,” Jul. 2024. doi: 10.48550/arXiv.2407.11852.

[2] A. Avignone, A. Tierno, A. Fiori, and S. Chiusano, “Exploring Large Language Models’ Ability to Describe Entity-Relationship Schema-Based Conceptual Data Models,” Information, vol. 16, no. 5, p. 368, Apr. 2025, doi: 10.3390/info16050368. DOI: https://doi.org/10.3390/info16050368

[3] S. P. and A. P. Shaji, “A Survey on Semantic Similarity,” in 2019 International Conference on Advances in Computing, Communication and Control (ICAC3), IEEE, Dec. 2019, pp. 1–8. doi: 10.1109/ICAC347590.2019.9036843. DOI: https://doi.org/10.1109/ICAC347590.2019.9036843

[4] Y. Zhang et al., “Schema Matching using Pre-Trained Language Models,” in 2023 IEEE 39th International Conference on Data Engineering (ICDE), IEEE, Apr. 2023, pp. 1558–1571. doi: 10.1109/ICDE55515.2023.00123. DOI: https://doi.org/10.1109/ICDE55515.2023.00123

[5] A. Guruprakash, “Agentic Schema Convergence: An AI-Driven Pipeline for Combined Schema Design and Data Migration in Technology M&A,” 2026. doi: 10.2139/ssrn.7316998. DOI: https://doi.org/10.2139/ssrn.7316998

[6] M. Awais and M. Ayaz, “Agentic Large Language Models: A Systematic Review Of Architectures, Reasoning, And Multi-Agent Collaboration,” Int. J. Eng. Technol. Res. Manag., vol. 10, no. 09, pp. 158–182, Sep. 2026, doi: 10.67809/ijetrm.1789357569. DOI: https://doi.org/10.67809/ijetrm.1789357569

[7] A. A., A. Nordin, M. Alzeber, and A. Zaid, “A Survey of Schema Matching Research using Database Schemas and Instances,” Int. J. Adv. Comput. Sci. Appl., vol. 8, no. 10, pp. 102–111, 2017, doi: 10.14569/IJACSA.2017.081014. DOI: https://doi.org/10.14569/IJACSA.2017.081014

[8] S. Jain and S. Tanwani, “Schema matching technique for heterogeneous web database,” in 2015 4th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions), IEEE, Sep. 2015, pp. 1–6. doi: 10.1109/ICRITO.2015.7359275. DOI: https://doi.org/10.1109/ICRITO.2015.7359275

[9] S. Mishra and S. Konidala, “Automated Data Mapping and Schema Matching For Improving Data Quality in Master Data Management.,” Int. J. Emerg. Trends Comput. Sci. Inf. Technol., vol. 4, no. 3, pp. 80–90, 2023, doi: 10.63282/3050-9246.IJETCSIT-V4I3P109. DOI: https://doi.org/10.63282/3050-9246.IJETCSIT-V4I3P109

[10] Z. H. Amur, Y. Kwang Hooi, H. Bhanbhro, K. Dahri, and G. M. Soomro, “Short-Text Semantic Similarity (STSS): Techniques, Challenges and Future Perspectives,” Appl. Sci., vol. 13, no. 6, p. 3911, Mar. 2023, doi: 10.3390/app13063911. DOI: https://doi.org/10.3390/app13063911

[11] S.-H. Wu and C.-Y. Yeh, “A Short Answer Grading System in Chinese by CNN,” in 2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST), IEEE, Oct. 2019, pp. 1–5. doi: 10.1109/ICAwST.2019.8923528. DOI: https://doi.org/10.1109/ICAwST.2019.8923528

[12] D. Li, J. Zhang, and P. Li, “Representation Learning for Question Classification via Topic Sparse Autoencoder and Entity Embedding,” in 2018 IEEE International Conference on Big Data (Big Data), IEEE, Dec. 2018, pp. 126–133. doi: 10.1109/BigData.2018.8622331. DOI: https://doi.org/10.1109/BigData.2018.8622331

[13] H. Tayyar Madabushi, M. Lee, and J. Barnden, “Integrating Question Classification and Deep Learning for improved Answer Selection,” in Proceedings of the 27th International Conference on Computational Linguistics, E. M. Bender, L. Derczynski, and P. Isabelle, Eds., Santa Fe, New Mexico, USA: Association for Computational Linguistics, Aug. 2018, pp. 3283–3294.

[14] D. Li et al., “Contextualized Perturbation for Textual Adversarial Attack,” in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, K. Toutanova, A. Rumshisky, L. Zettlemoyer, D. Hakkani-Tur, I. Beltagy, S. Bethard, R. Cotterell, T. Chakraborty, and Y. Zhou, Eds., Stroudsburg, PA, USA, PA, USA: Association for Computational Linguistics, Jun. 2021, pp. 5053–5069. doi: 10.18653/v1/2021.naacl-main.400. DOI: https://doi.org/10.18653/v1/2021.naacl-main.400

[15] D. S. Sachan, M. Zaheer, and R. Salakhutdinov, “Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function,” Proc. AAAI Conf. Artif. Intell., vol. 33, no. 01, pp. 6940–6948, Jul. 2019, doi: 10.1609/aaai.v33i01.33016940. DOI: https://doi.org/10.1609/aaai.v33i01.33016940

[16] M. Munikar, S. Shakya, and A. Shrestha, “Fine-grained Sentiment Classification using BERT,” in 2019 Artificial Intelligence for Transforming Business and Society (AITB), IEEE, Nov. 2019, pp. 1–5. doi: 10.1109/AITB48515.2019.8947435. DOI: https://doi.org/10.1109/AITB48515.2019.8947435

[17] D. Chandrasekaran and V. Mago, “Evolution of Semantic Similarity—A Survey,” ACM Comput. Surv., vol. 54, no. 2, pp. 1–37, Mar. 2022, doi: 10.1145/3440755. DOI: https://doi.org/10.1145/3440755

[18] T. Wei et al., “A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents,” Sep. 2026. doi: 10.48550/arXiv.2601.12538.

[19] M. Parciak, B. Vandevoort, F. Neven, L. M. Peeters, and S. Vansummeren, “LLM-Matcher: A Name-Based Schema Matching Tool using Large Language Models,” in Companion of the 2025 International Conference on Management of Data, in SIGMOD/PODS ’25. New York, NY, USA, NY, USA, NY, USA: ACM, Jun. 2025, pp. 203–206. doi: 10.1145/3722212.3725112. DOI: https://doi.org/10.1145/3722212.3725112

[20] S. Wang et al., “LLMATCH: A Unified Schema Matching Framework with Large Language Models,” Jul. 2025. doi: 10.48550/arXiv.2507.10897. DOI: https://doi.org/10.1007/978-981-95-5722-6_37

[21] N. Seedat and M. van der Schaar, “Matchmaker: Self-Improving Large Language Model Programs for Schema Matching,” Oct. 2024. doi: 10.48550/arXiv.2410.24105.

[22] E. Wu et al., “BDIViz: An Interactive Visualization System for Biomedical Schema Matching with LLM-Powered Validation,” IEEE Trans. Vis. Comput. Graph., vol. 32, no. 1, pp. 1208–1218, Jan. 2026, doi: 10.1109/TVCG.2025.3634843. DOI: https://doi.org/10.1109/TVCG.2025.3634843

[23] M. Raoui, M. H. El Yazidi, and A. Zellou, “SchemaML: Semantic Schema Matching for Enhanced Data Interoperability,” in 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET), IEEE, Jul. 2026, pp. 1–6. doi: 10.1109/ICECET65726.2026.11632351. DOI: https://doi.org/10.1109/ICECET65726.2026.11632351

[24] Y. Qu, C. Ma, Y. Chang, F. Pan, L. Tang, and S. Zhu, “Database Schema Matching Model Based on Multimodal Fusion Analysis,” in 2025 5th Asia Conference on Information Engineering (ACIE), IEEE, Jan. 2025, pp. 32–36. doi: 10.1109/ACIE64499.2025.00012. DOI: https://doi.org/10.1109/ACIE64499.2025.00012

[25] D. Pinto, L. Feremans, F. Neven, M. Parciak, and S. Vansummeren, “LLM-generated Schema Matching with Formally Verifiable Explanations,” in 2026 IEEE 42nd International Conference on Data Engineering Workshops (ICDEW), IEEE, May 2026, pp. 176–186. doi: 10.1109/ICDEW71238.2026.00023. DOI: https://doi.org/10.1109/ICDEW71238.2026.00023

[26] M. Raoui, L. Rassam, M. H. El Yazidi, and A. Zellou, “Automated Interoperability based on Decision Tree for Schema Matching,” in 2022 International Conference on Computational Modelling, Simulation and Optimization (ICCMSO), IEEE, Dec. 2022, pp. 48–52. doi: 10.1109/ICCMSO58359.2022.00023. DOI: https://doi.org/10.1109/ICCMSO58359.2022.00023