CFP last date
22 December 2025
Call for Paper
January Edition
IJCA solicits high quality original research papers for the upcoming January edition of the journal. The last date of research paper submission is 22 December 2025

Submit your paper
Know more
The week's pick
Responsive image
A Hybrid Transformer-CNN Framework with Early and Late Fusion for Robust Skin Lesion Classification

Raihan Tanvir
Random Articles
Reseach Article

RAG-based AI Agents for Multilingual Help Desks in Low-Bandwidth Environments

by Ajay Guyyala, Prudhvi Ratna Badri Satya, Vijay Putta, Krishna Teja Areti
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Number 56
Year of Publication: 2025
Authors: Ajay Guyyala, Prudhvi Ratna Badri Satya, Vijay Putta, Krishna Teja Areti
10.5120/ijca2025925964

Ajay Guyyala, Prudhvi Ratna Badri Satya, Vijay Putta, Krishna Teja Areti . RAG-based AI Agents for Multilingual Help Desks in Low-Bandwidth Environments. International Journal of Computer Applications. 187, 56 ( Nov 2025), 15-28. DOI=10.5120/ijca2025925964

@article{ 10.5120/ijca2025925964,
author = { Ajay Guyyala, Prudhvi Ratna Badri Satya, Vijay Putta, Krishna Teja Areti },
title = { RAG-based AI Agents for Multilingual Help Desks in Low-Bandwidth Environments },
journal = { International Journal of Computer Applications },
issue_date = { Nov 2025 },
volume = { 187 },
number = { 56 },
month = { Nov },
year = { 2025 },
issn = { 0975-8887 },
pages = { 15-28 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume187/number56/rag-based-ai-agents-for-multilingual-help-desks-in-low-bandwidth-environments/ },
doi = { 10.5120/ijca2025925964 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2025-11-18T21:11:06.808161+05:30
%A Ajay Guyyala
%A Prudhvi Ratna Badri Satya
%A Vijay Putta
%A Krishna Teja Areti
%T RAG-based AI Agents for Multilingual Help Desks in Low-Bandwidth Environments
%J International Journal of Computer Applications
%@ 0975-8887
%V 187
%N 56
%P 15-28
%D 2025
%I Foundation of Computer Science (FCS), NY, USA
Abstract

The increasing demand for multilingual help desk systems has prompted the need for advanced solutions that can provide accurate, real time responses across various languages. This paper presents a retrieval-augmented generation (RAG) based system optimized for low-bandwidth environments. The proposed system integrates retrieval techniques with generative models, enabling it to generate contextually relevant responses while minimizing latency. To address the challenge of low-bandwidth operation, model distillation and token compression methods are introduced, which reduce model size and response time. The system’s performance is evaluated on multilingual datasets, demonstrating substantial improvements over baseline models in terms of accuracy, recall, precision, and F1-Score. The challenges of multilingual support, retrieval accuracy, and low-latency performance are effectively tackled by this approach, making it a viable solution for real-time customer support in resource-constrained settings. The findings suggest that the proposed system can serve as a robust platform for multilingual help desks, offering improved scalability and efficiency. The system was built using a hybrid retriever– generator architecture, with a cross-lingual transformer for retrieval and a transformer-based sequence-to-sequence model for generation. Multilingual datasets, including TyDiQA, mMARCO, XQuAD, MLDoc, and AfriSenti, were used for training and evaluation. Low-bandwidth optimization techniques such as model distillation and token compression were applied.The proposed system achieved higher EM, BLEU, and MRR scores than baseline models, with EM of 79.2%, BLEU of 32.8, and MRR of 0.80, while reducing latency from 3.4s in the baseline to 2.1s. The distilled model further reduced latency to 1.8s with minor performance trade-offs. Error analysis showed reduced hallucination rates and improved relevance in responses for low-resource languages.

References
  1. Oluwafemi Akanfe, Paras Bhatt, and Diane A Lawong. Technology advancements shaping the financial inclusion landscape: Present interventions, emergence of artificial intelligence and future directions. Information Systems Frontiers, pages 1–24, 2025.
  2. George C Alexandropoulos, Dinh-Thuy Phan-Huy, Konstantinos D Katsanos, Maurizio Crozzoli, Henk Wymeersch, Petar Popovski, Philippe Ratajczak, Yohann B´en´edic, Marie-Helene Hamon, Sebastien Herraiz Gonzalez, et al. Risenabled smart wireless environments: Deployment scenarios, network architecture, bandwidth and area of influence. EURASIP Journal on Wireless Communications and Networking, 2023(1):103, 2023.
  3. Lilach Alon and Maja Krtali´c. “i wish i could use any language as it comes to mind”: User experience in digital platforms in the context of multilingual personal information management. Journal of the Association for Information Science and Technology, 76(4):686–702, 2025.
  4. Laith Alzubaidi, Jinshuai Bai, Aiman Al-Sabaawi, Jose Santamar´ıa, Ahmed Shihab Albahri, Bashar Sami Nayyef Al-Dabbagh, Mohammed A Fadhel, Mohamed Manoufali, Jinglan Zhang, Ali H Al-Timemy, et al. A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. Journal of Big Data, 10(1):46, 2023.
  5. Nivas Annamareddy, Lahari Parvathaneni, Jaisri Putta, Lakshmi Donepudi, KBV Brahma Rao, and Pachipala Yellamma. Advancing multilingual communication: Real-time language translation in social media platforms leveraging advanced machine learning models. Journal of Chemical Health Risks (JCHR), 14(3):25–35, 2024.
  6. Awa Babington-Ashaye, Philippe de Moerloose, Saliou Diop, and Antoine Geissbuhler. Design, development and usability of an educational ai chatbot for people with haemophilia in senegal. Haemophilia, 29(4):1063–1073, 2023.
  7. Mamatha Balipa, K Anwaya, M Murugappan, et al. A rulebased machine translation framework for low-resource language pairs. In 2025 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL), pages 969–974. IEEE, 2025.
  8. Rajat Kumar Behera, Pradip Kumar Bala, and Arghya Ray. Cognitive chatbot for personalised contextual customer service: Behind the scene and beyond the hype. Information Systems Frontiers, 26(3):899–919, 2024.
  9. Berhanu Bogale, Tesfa Tegegne, Solomon Teferra, and Gebeyehu Belay. Rag based qa for low resource languages. 2024.
  10. Chen-Chi Chang, Chong-Fu Li, Chu-Hsuan Lee, and Hung- Shin Lee. Enhancing low-resource minority language translation with llms and retrieval-augmented generation for cultural nuances. arXiv preprint arXiv:2505.10829, 2025.
  11. Nadezhda Chirkova, David Rau, Herv´e D´ejean, Thibault Formal, St´ephane Clinchant, and Vassilina Nikoulina. Retrievalaugmented generation in multilingual settings. arXiv preprint arXiv:2407.01463, 2024.
  12. Kan Feng, Lijun Luo, Yongjun Xia, Bin Luo, Xingfeng He, Kaihong Li, Zhiyong Zha, Bo Xu, and Kai Peng. Optimizing microservice deployment in edge computing with large language models: Integrating retrieval augmented generation and chain of thought techniques. Symmetry, 16(11):1470, 2024.
  13. Rena Huseynova, Narmin Aliyeva, Konul Habibova, and Rasim Heydarov. The evolution of the english language in the internet and social media era. Cadernos de Educac¸ ˜ao Tecnologia e Sociedade, 17(se4):299–314, 2024.
  14. Saverio Ieva, Davide Loconte, Giuseppe Loseto, Michele Ruta, Floriano Scioscia, Davide Marche, and Marianna Notarnicola. A retrieval-augmented generation approach for data-driven energy infrastructure digital twins. Smart Cities, 7(6):3095–3120, 2024.
  15. Junfeng Jiao, Jihyung Park, Yiming Xu, Kristen Sussman, and Lucy Atkinson. Safemate: A modular rag-based agent for context-aware emergency guidance. arXiv preprint arXiv:2505.02306, 2025.
  16. Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Akari Asai, Xinyan Yu, Dragomir Radev, Noah A Smith, Yejin Choi, Kentaro Inui, et al. Realtime qa: What’s the answer right now? Advances in neural information processing systems, 36:49025– 49043, 2023.
  17. Abdullah Ayub Khan, Jing Yang, Asif Ali Laghari, Abdullah M Baqasah, Roobaea Alroobaea, Chin Soon Ku, Roohallah Alizadehsani, U Rajendra Acharya, and Lip Yee Por. Baiot-ems: Consortium network for small-medium enterprises management system with blockchain and augmented intelligence of things. Engineering Applications of Artificial Intelligence, 141:109838, 2025.
  18. Michael Klesel and H Felix Wittmann. Retrieval-augmented generation (rag) m. klesel, hf wittmann. Business & Information Systems Engineering, pages 1–11, 2025.
  19. Qing Li, Xun Tang, Junkun Peng, Yuanzheng Tan, and Yong Jiang. Latency reducing in real-time internet video transport: A survey. Available at SSRN 4654242, 2023.
  20. Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yuyao Zhang, Peitian Zhang, Yutao Zhu, and Zhicheng Dou. From matching to generation: A survey on generative information retrieval. ACM Transactions on Information Systems, 43(3):1–62, 2025.
  21. Shalev Lifshitz, Keiran Paster, Harris Chan, Jimmy Ba, and Sheila McIlraith. Steve-1: A generative model for text-tobehavior in minecraft. Advances in Neural Information Processing Systems, 36:69900–69929, 2023.
  22. Zlatan Mori´c, Leo Mrˇsi´c, Mario Filjak, and Goran DJambic. Integrating a virtual assistant by using the rag method and vertex ai framework at algebra university. Applied Sciences (2076-3417), 14(22), 2024.
  23. Edmund V Ndimbo, Qin Luo, Gimo C Fernando, Xu Yang, and Bang Wang. Leveraging retrieval-augmented generation for swahili language conversation systems. Applied Sciences, 15(2):524, 2025.
  24. Antoine Nzeyimana and Andre Niyongabo Rubungo. Kinyacolbert: A lexically grounded retrieval model for lowresource retrieval-augmented generation. arXiv preprint arXiv:2507.03241, 2025.
  25. George Papageorgiou, Vangelis Sarlis, Manolis Maragoudakis, and Christos Tjortjis. Hybrid multi-agent graphrag for e-government: Towards a trustworthy ai assistant. Applied Sciences, 15(11):6315, 2025.
  26. Sunil Kumar Parisa and Somnath Banerjee. Ai-enabled cloud security solutions: A comparative review of traditional vs. next-generation approaches. International Journal of Statistical Computation and Simulation, 16(1), 2024.
  27. Irina Radeva, Ivan Popchev, Lyubka Doukovska, and Miroslava Dimitrova. Web application for retrievalaugmented generation: Implementation and testing. Electronics, 13(7):1361, 2024.
  28. Leonardo Ranaldi, Barry Haddow, and Alexandra Birch. Multilingual retrieval-augmented generation for knowledgeintensive task. arXiv preprint arXiv:2504.03616, 2025.
  29. N Reddy. Design and implementation of an ai-based chatbot framework with retrieval-augmented generation and integrated recommender system for interactive user support. Available at SSRN 5250507, 2025.
  30. AMFZ Salih. Language barriers and their impact on effective communication in different fields. Journal of Advancement of Social Science and Humanity, pages 22–32, 2024.
  31. Cody H Savage, Adway Kanhere, Vishwa Parekh, Curtis P Langlotz, Anupam Joshi, Heng Huang, and Florence X Doo. Open-source large language models in radiology: a review and tutorial for practical research and clinical deployment. Radiology, 314(1):e241073, 2025.
  32. Holger Schwenk and Xian Li. A corpus for multilingual document classification in eight languages. In Nicoletta Calzolari (Conference chair), Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Koiti Hasida, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H´el`ene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis, and Takenobu Tokunaga, editors, Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France, may 2018. European Language Resources Association (ELRA).
  33. Mahaboobsubani Shaik. Advanced neural networks for multilingual customer service. IJLRP-International Journal of Leading Research Publication, 5(10), 2024.
  34. Rohit Singh, Santosh Grampurohit, Keshav Kumar, Chandan Kumar Singh, Sk Mohammad Arif, and Sourajit Bhar. A multilingual intelligent document question-answering system. 2025.
  35. Medapati Venkata Manga Naga Sravan and Venkata Rao. 5goptimized deep learning framework for real-time multilingual speech-to-speech translation in telemedicine systems. Informatica, 49(2), 2025.
  36. Lanjun Wan, Weihua Zheng, and Xinpan Yuan. Efficient inter-device task scheduling schemes for multi-device coprocessing of data-parallel kernels on heterogeneous systems. IEEE Access, 9:59968–59978, 2021.
  37. Gaike Wang, Qiwen Zhao, Zhongwen Zhou, and Yibang Liu. Research on real-time multilingual transcription and minutes generation for video conferences based on large language models. Spectrum of Research, 5(1), 2025.
  38. Suhang Wu, Jialong Tang, Baosong Yang, Ante Wang, Kaidi Jia, Jiawei Yu, Junfeng Yao, and Jinsong Su. Not all languages are equal: Insights into multilingual retrieval-augmented generation. arXiv preprint arXiv:2410.21970, 2024.
  39. Wayne Xin Zhao, Jing Liu, Ruiyang Ren, and Ji-Rong Wen. Dense text retrieval based on pretrained language models: A survey. ACM Transactions on Information Systems, 42(4):1– 60, 2024.
  40. Yiran Zhao, Wenxuan Zhang, Guizhen Chen, Kenji Kawaguchi, and Lidong Bing. How do large language models handle multilingualism? Advances in Neural Information Processing Systems, 37:15296–15319, 2024.
Index Terms

Computer Science
Information Sciences

Keywords

Multilingual Help Desk Systems Retrieval-Augmented Generation (RAG) Low-Bandwidth Optimization Model Distillation Techniques Token Compression for NLP Cross-Lingual Information Retrieval Transformer-Based Generative Models Multilingual Benchmark Datasets Real-Time Response Generation Latency Reduction in NLP Systems

Powered by PhDFocusTM