Enhancing Email Intent Filtering Using Agentic AI-Based Model Selection

This study presented a comparative analysis of traditional machine learning and an agentic AI approach for email intent filtering. The traditional method, which relies on a single predefined model, was found to have limitations in terms of adaptability and performance. In contrast, the proposed agentic AI system demonstrated the ability to dynamically evaluate multiple models and select the most suitable one based on performance metrics. Experimental results showed that the agentic approach successfully identified Linear Support Vector Machine (Linear SVM) as the best-performing model, leading to improved accuracy and more balanced predictions compared to the traditional model. This highlights the effectiveness of automated model selection in enhancing classification performance. Furthermore, the use of a larger dataset contributed to more reliable and realistic evaluation, enabling the models to learn meaningful patterns from email data. The findings confirm that agentic AI systems offer significant advantages in terms of adaptability, reduced bias, and improved learning capability. The proposed approach demonstrates that agentic AI is a more efficient and flexible solution for email intent filtering compared to traditional methods. Future work can focus on integrating advanced techniques such as deep learning and contextual embeddings to further improve performance and scalability in real-world applications.

[1] Emmanuel Gbenga Dada, Joseph Stephen Bassi, HarunaChiroma, Shafi'i Muhammad Abdulhamid, Adebayo OlusolaAdetunmbi, Opeyemi Emmanuel Ajibuwa, “Machine learning for email spam filtering: review, approaches and open research problems”, Heliyon,Volume 5, Issue 6,2019, e01802, ISSN 2405-8440, https://doi.org/10.1016/j.heliyon.2019.e01802. [2] Mr. DIVYA SREE .A.M, Mrs. DEEPA.A, “Intelligent Email Filtering with NLP and Machine Learning”, International Journal of Research Publication and Reviews , Vol (6), Issue (3), March (2025), Page – 6748-6750 , ISSN 2582-7421. [3] N. M. Devi, V. Asha, D. Dhiman, P. Patil, P. Utkarsh and V. Poojari, "Email Security Enhancement via ML-based Spam Filter Techniques," 2025 6th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), Tirunelveli, India, 2025, pp. 336-340, doi: 10.1109/ICICV64824.2025.11086034.Bottom of Form [4] A.Sesha Rao, P.S.Avadhani, NanditaBhanja Chaudhuri, "A Content-Based Spam E-Mail Filtering Approach Using Multilayer Percepton Neural Networks," International Journal of Engineering Trends and Technology (IJETT), vol. 41, no. 1, pp. 44-55, 2016. Crossref, https://doi.org/10.14445/22315381/IJETT-V41P210. [5] E. Eilertsen, V. Mavroeidis and G. Grov, "LLM-Powered Intent-Based Categorization of Phishing Emails," 2025 IEEE International Conference on Cyber Security and Resilience (CSR), Chania, Crete, Greece, 2025, pp. 753-758, doi: 10.1109/CSR64739.2025.11130105. [6]Kai Shu, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah, MiladShokouhi, and Susan Dumais. 2020. Learning with Weak Supervision for Email Intent Detection. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20). Association for Computing Machinery, New York, NY, USA, 1051–1060. https://doi.org/10.1145/3397271.3401121. [7] Alibadi, Z.(2021). Detecting the Intent of Email Using Embeddings, Deep Learning and Transfer Learning. (Doctoral dissertation). Retrieved from https://scholarcommons.sc.edu/etd/6384. [8] Rahul Kavi, Jeevan Anne,“INTENT RECOGNITION USING DISTILBERT AND LANGUAGE MODELS”,Journal of Artificial Intelligence and Machine Learning (JAIML),Volume=3&Issue=2 .Journal ID: 5979-A561, DOI: https://doi.org/10.5281/zenodo.13996032. [9] M. Sappelli, G. Pasi, S. Verberne, M. de Boer, W. Kraaij, “Assessing e-mail intent and tasks in e-mail messages”, Information Sciences, Volumes 358–359, 2016, Pages 1-17, ISSN 0020-0255, https://doi.org/10.1016/j.ins.2016.03.002. [10] RamyaAtchuta, Chandrika Rajulapati, KurmaraoSurni, Yaswanth Reddy Puritipati, S V Manikanta Tagore Yerrapothu,” CONTEXT-AWARE EMAIL AUTOMATION USING AGENTIC AI AND LARGE LANGUAGE MODELS”, International Journal of Creative Research Thoughts (IJCRT), Volume 14, Issue 4 April 2026 | ISSN: 2320-2882.