{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T13:22:58Z","timestamp":1772544178417,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OIA-1946391"],"award-info":[{"award-number":["OIA-1946391"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Entity resolution in real-world datasets remains a persistent challenge, particularly for identifying households and detecting co-residence patterns within noisy and incomplete data. While Large Language Models (LLMs) show promise, monolithic approaches often suffer from limited scalability and interpretability. This study introduces a multi-agent Retrieval-Augmented Generation (RAG) framework that decomposes household entity resolution into coordinated, task-specialized agents implemented using LangGraph. The system includes four agents responsible for direct matching, transitive linkage, household clustering, and residential movement detection, combining rule-based preprocessing with LLM-guided reasoning. Evaluation on synthetic S12PX dataset segments containing 200\u2013300 records demonstrates 94.3% accuracy on name variation matching and a 61% reduction in API calls compared to single-LLM baselines, while maintaining transparent and traceable decision processes. These results indicate that coordinated multi-agent specialization improves efficiency and interpretability, providing a structured and extensible approach for entity resolution in census, healthcare, and other administrative data domains.<\/jats:p>","DOI":"10.3390\/computers14120525","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T16:07:38Z","timestamp":1764864458000},"page":"525","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Agent RAG Framework for Entity Resolution: Advancing Beyond Single-LLM Approaches with Specialized Agent Coordination"],"prefix":"10.3390","volume":"14","author":[{"given":"Aatif Muhammad","family":"Althaf","sequence":"first","affiliation":[{"name":"Center for Advanced Research in Entity Resolution and Information Quality (ERIQ), University of Arkansas, Little Rock, AR 72204, USA"}]},{"given":"Muzakkiruddin Ahmed","family":"Mohammed","sequence":"additional","affiliation":[{"name":"Center for Advanced Research in Entity Resolution and Information Quality (ERIQ), University of Arkansas, Little Rock, AR 72204, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0995-1921","authenticated-orcid":false,"given":"Mariofanna","family":"Milanova","sequence":"additional","affiliation":[{"name":"Center for Advanced Research in Entity Resolution and Information Quality (ERIQ), University of Arkansas, Little Rock, AR 72204, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1004-0965","authenticated-orcid":false,"given":"John","family":"Talburt","sequence":"additional","affiliation":[{"name":"Center for Advanced Research in Entity Resolution and Information Quality (ERIQ), University of Arkansas, Little Rock, AR 72204, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0018-9693","authenticated-orcid":false,"given":"Mert Can","family":"Cakmak","sequence":"additional","affiliation":[{"name":"Center for Advanced Research in Entity Resolution and Information Quality (ERIQ), University of Arkansas, Little Rock, AR 72204, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Christen, P. (2012). Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection, Springer.","DOI":"10.1007\/978-3-642-31164-2"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","article-title":"Duplicate record detection: A survey","volume":"19","author":"Elmagarmid","year":"2007","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_3","first-page":"1","article-title":"Entity resolution and social networks","volume":"5","author":"Getoor","year":"2012","journal-title":"Synth. Lect. Data Min. Knowl. Discov."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3377455","article-title":"Blocking and filtering techniques for entity resolution: A survey","volume":"53","author":"Papadakis","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref_5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_6","unstructured":"OpenAI (2024). GPT-4 Technical Report. arXiv."},{"key":"ref_7","unstructured":"Zhang, Y., Pei, J., Sun, Y., Li, Y., Lin, C., Su, L., and Liu, Y. (2023). LLM-ER: Large language models for entity resolution. arXiv."},{"key":"ref_8","unstructured":"Chen, X., Li, Q., Jiang, Y., Zhang, T., Chen, J., and Xu, L. (2023). Contextual entity resolution with large language models. arXiv."},{"key":"ref_9","unstructured":"Weng, L. (2023). Large language models are zero-shot reasoners with multi-agent collaboration. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (2023). Generative agents: Interactive simulacra of human behavior. arXiv.","DOI":"10.1145\/3586183.3606763"},{"key":"ref_11","first-page":"9459","article-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2226","DOI":"10.1109\/TAI.2025.3544173","article-title":"Multi-Agent Actor-Critic Generative AI for Query Resolution and Analysis","volume":"6","author":"Rahman","year":"2025","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_13","unstructured":"Li, Z., Wang, T., and Wang, L. (2024). Multi-agent retrieval-augmented generation for complex question answering. arXiv."},{"key":"ref_14","unstructured":"Zhou, Y., Wang, X., and Huang, M. (2023). Agents of change: Multi-agent systems in the age of large language models. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Talburt, J.R. (2011). Entity Resolution and Information Quality, Elsevier.","DOI":"10.1016\/B978-0-12-381972-7.00003-8"},{"key":"ref_16","unstructured":"Saeedi, A., Peukert, E., and Rahm, E. (June, January 31). Incremental Multi-Source Entity Resolution for Knowledge Graph Completion. Proceedings of the European Semantic Web Conference, Heraklion, Greece."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lin, Y., Li, H., Liu, S., Han, J., and Han, S. (2021). Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations. arXiv.","DOI":"10.18653\/v1\/2021.ecnlp-1.6"},{"key":"ref_18","unstructured":"Fang, L., Chen, M., Yu, L., Xu, W., and Zhang, C. (2023). KAER: A Knowledge-Augmented Pre-Trained Language Model for Entity Resolution. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kasai, J., Qian, X., Gururangan, S., and Smith, N.A. (2019). Low-Resource Deep Entity Resolution with Transfer and Active Learning. arXiv.","DOI":"10.18653\/v1\/P19-1586"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, X., Fan, S., Yao, J., and Sun, H. (2025). Contextual Semantics Graph Attention Network Model for Entity Resolution. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-11932-9"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chen, Z., Kalashnikov, D.V., and Mehrotra, S. (July, January 29). Exploiting Context Analysis for Combining Multiple Entity Resolution Systems. Proceedings of the 2009 ACM SIGMOD International Conference on Management of Data, Providence, RI, USA.","DOI":"10.1145\/1559845.1559869"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102609","DOI":"10.1016\/j.is.2025.102609","article-title":"CrossER: A Robust and Adaptable Generalized Entity Resolution Framework for Diverse and Heterogeneous Datasets","volume":"135","author":"Tian","year":"2025","journal-title":"Inf. Syst."},{"key":"ref_23","first-page":"75","article-title":"An Advanced Entity Resolution in Data Lakes: First Steps","volume":"234","author":"Bouabdelli","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_24","unstructured":"Mohammed, M.A., Talburt, J.R., Althaf, A.M., and Milanova, M. (2025, January 4\u20137). Multi-LLM Record Linkage: A Comparative Analysis Framework for Co-Residence Pattern Discovery. Proceedings of the 12th Annual Conference on Computational Science and Computational Intelligence (CSCI 2025), Haikou, China."},{"key":"ref_25","unstructured":"Latifi, S. (2025, January 13\u201316). Entity Resolution with Household Movement Discovery Using Google Generative AI. Proceedings of the 22nd International Conference on Information Technology\u2013New Generations (ITNG 2025), Advances in Intelligent Systems and Computing, Las Vegas, NV, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kim, J., Ko, D., and Kim, G. (2024). DynamicER: Resolving Emerging Mentions to Dynamic Entities for Retrieval-Augmented Generation. arXiv.","DOI":"10.18653\/v1\/2024.emnlp-main.762"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"De Cao, N., Aziz, W., and Titov, I. (2021). Highly Parallel Autoregressive Entity Linking with Discriminative Correction. arXiv.","DOI":"10.18653\/v1\/2021.emnlp-main.604"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ding, Y., Sun, M., and Gao, L. (2024). Rethinking Negative Instances for Generative Named Entity Recognition. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.206"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Deu\u00dfer, T., Kaltenbrunner, R., and Zimmermann, R. (2024, January 15\u201318). Informed Named Entity Recognition Decoding for Generative Language Models. Proceedings of the 2024 IEEE International Conference on Big Data, Washington, DC, USA.","DOI":"10.1109\/BigData62323.2024.10825603"},{"key":"ref_30","unstructured":"Guo, L., Zhang, X., and Li, Z. (2023). Revisit and Outstrip Entity Alignment: A Perspective of Generative Models. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Huang, S., Zhang, L., and Chen, D. (2024, January 21\u201325). From Retrieval to Generation: Efficient and Effective Entity Set Expansion. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, Boise, ID, USA.","DOI":"10.1145\/3627673.3679837"},{"key":"ref_32","first-page":"102160","article-title":"Benchmarking Entity Resolution Datasets: Revisiting Assumptions and Limitations","volume":"115","author":"Papadakis","year":"2023","journal-title":"Inf. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chuang, Y.-S., Lee, Y.-T., and Yu, H.-Y. (2024). Cross-Institutional Dental Electronic Health Record Entity Extraction via Generative Artificial Intelligence and Synthetic Notes. J. Biomed. Inform., 8.","DOI":"10.1093\/jamiaopen\/ooaf061"},{"key":"ref_34","unstructured":"Wu, L., Li, X., and Song, D. (2020, January 6\u201310). Unsupervised Entity Matching with Rich Contextual Information. Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event."},{"key":"ref_35","unstructured":"Nguyen, T., Chin, P., and Tai, Y.-W. (2025). MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Liu, P., Liu, X., Yao, R., Liu, J., Meng, S., Wang, D., and Ma, J. (2025). HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval-Augmented Generation. arXiv.","DOI":"10.1145\/3746027.3754761"},{"key":"ref_37","unstructured":"Salve, A., Attar, S., Deshmukh, M., Shivpuje, S., and Utsab, A.M. (2024). A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chang, C.-Y., Jiang, Z., Rakesh, V., Pan, M., Yeh, C.-C.M., Wang, G., Hu, M., Xu, Z., Zheng, Y., and Das, M. (2024). MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation. arXiv.","DOI":"10.18653\/v1\/2025.acl-long.131"},{"key":"ref_39","unstructured":"Mohammed, M.A., Talburt, J.R., Claasssens, L., and Marais, A. (2025, January 6\u20138). Retrieval-Augmented Multi-LLM Ensemble for Industrial Part Specification Extraction. Proceedings of the 17th International Conference on Knowledge and Systems Engineering (KSE 2025), Dalat, Vietnam."},{"key":"ref_40","unstructured":"Al Mandalawi, S., Mohammed, M.A., Maclean, H., Cakmak, M.C., and Talburt, J.R. (2025, January 6\u20138). Policy-Aware Generative AI for Safe, Auditable Data Access Governance. Proceedings of the 17th International Conference on Knowledge and Systems Engineering (KSE 2025), Dalat, Vietnam."},{"key":"ref_41","unstructured":"Mohammed, M.A., Al Mandalawi, S., Maclean, H., and Talburt, J.R. (2025, January 3\u20135). Multilingual Customer Record Linkage: A Novel Approach Using LLMs for Cross-Lingual Entity Resolution. Proceedings of the 12th Annual Conference on Computational Science and Computational Intelligence (CSCI 2025), Las Vegas, NV, USA."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/525\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T16:16:45Z","timestamp":1764865005000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":41,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["computers14120525"],"URL":"https:\/\/doi.org\/10.3390\/computers14120525","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}