A multi-agent artificial intelligence-powered architecture for customer experience management
Matendo Didas1
Center for Information and Communication Technology,St. John's University of Tanzania, Kikuyu Ave,Dodoma,Tanzania1
Corresponding Author : Matendo Didas
Recieved : 16-October-2025; Revised : 18-January-2026; Accepted : 24-January-2026
Abstract
Customer experience management (CXM), which directly affects revenue growth, customer retention, and customer happiness, is an essential component of modern business planning. In the digital economy, CXM is now a critical component that determines an organization's success. However, as data volumes and customer engagement channels grow dramatically, traditional CXM systems such as help desk software, customer feedback management, and ticketing systems have become less able to provide scalable, real-time responsiveness and personalized customer experiences (CX). In addition to potential biases or errors that could lead to unhappy customers and reputational harm, these single-agent-driven architectures frequently suffer from a lack of empathy, complexity, limited adaptability, inadequate integration, and data privacy problems. In response to these challenges, the paper investigated a multi-agent intelligent system (MAIS) innovation for CXM by creating the multi-agent artificial intelligence (MAAI)-powered architecture for CXM to guide addressing these issues. The design science research methodology (DSRM), which is renowned for directing advances in information technology (IT) and information systems (IS) through the creation of innovative artifacts, was used in this study. Autonomous software agents that improve decision-making, automate interactions, and provide customized CX are integrated into the suggested MAAI architecture. To guarantee seamless and flexible client interactions, each agent carries out specific tasks like sentiment analysis (SA), behavior prediction, service recommendation, and real-time customer care. The study offers a thorough MAAI architecture that recognizes and incorporates the essential agentic components needed to direct the deployment of a successful MAAI system for CXM. Together, these components make it possible for customer interaction procedures to be dynamic, adaptable, and scalable, which solves the drawbacks of conventional CXM systems. By directing and enabling intelligent, data-driven, and compassionate customer interactions, the suggested MAAI architecture has the potential to completely transform CXM. To verify the architecture's efficacy, future work can take into consideration the prototype creation and testing in a retail simulation. Improved response times, increased customer happiness, and increased operational effectiveness are some of the anticipated results metrics.
Keywords
Multi-agent systems, Customer experience management, Artificial intelligence, Machine learning, Natural language processing, Autonomous agents.
Cite this article
Didas M. A multi-agent artificial intelligence-powered architecture for customer experience management. International Journal of Advanced Computer Research. 2026;16(76):96-117. DOI : 10.19101/IJACR.2025.1570026
References
[1]
Athaide GA, Zhang JQ, Klink RR. Customer experience management (CXM) and new product success: an empirical investigation. European Journal of Innovation Management. 2025; 28(8):3648-60.
[2]
Da SRP. Customer experience and success management: assessing the maturity of CXM and CSM in companies and exploring the synergy between these emerging areas. Doctoral Dissertation, Universidade Federal Do Rio De Janeiro. 2024.
[3]
Krishna PM, Kumar TP, Reddy RV, Ariwa E. Customer-centric AI solutions. In Minds Unveiled 2024 (pp. 58-69). Productivity Press.
[4]
Enwe E. B2B firms and their customers: re-strategizing customer experience for competitive advantage. Master's Thesis, Faculty of Social Sciences and Business Studies, University of Eastern, Finland. 2020.
[5]
Lemon KN, Verhoef PC. Understanding customer experience throughout the customer journey. Journal of Marketing. 2016; 80(6):69-96.
[6]
Homburg C, Jozić D, Kuehnl C. Customer experience management: toward implementing an evolving marketing concept. Journal of the Academy of Marketing Science. 2017; 45(3):377-401.
[7]
Ordenes FV, Solis DD, Herhausen D. Customer experience measurement: implications for customer loyalty. In handbook of research on customer loyalty 2022 (pp. 83-94). Edward Elgar Publishing.
[8]
Ezechukwu MA, Chukwu E. Politeness in staff-clients interaction: a study of nnamdi azikiwe university service encounter. Multidisciplinary Journal of Law, Education and Humanities. 2025; 2(1):18-30.
[9]
Kunal K. Impact of AI in customer services retention: a behavioral perspective of Indian mobile market. Global Journal of Business and Integral Security. 2016.
[10]
Sharma A, Patel N, Gupta R. Enhancing customer experience personalization through AI: leveraging deep learning and collaborative filtering algorithms. European Advanced AI Journal. 2022; 11(9):1-26.
[11]
Kumar V, Reinartz W. Customer relationship management. 2018.
[12]
Gacanin H, Wagner M. Artificial intelligence paradigm for customer experience management in next-generation networks: Challenges and perspectives. IEEE Network. 2019; 33(2):188-94.
[13]
Hardcastle K, Vorster L, Brown DM. Understanding customer responses to AI-Driven personalized journeys: impacts on the customer experience. Journal of Advertising. 2025; 54(2):176-95.
[14]
Nalini R. Transformative power of artificial Intelligence in decision-making, automation, and customer engagement. In complex AI dynamics and interactions in management 2024 (pp. 189-208). IGI Global Scientific Publishing.
[15]
Davenport T, Guha A, Grewal D, Bressgott T. How artificial intelligence will change the future of marketing. Journal of the Academy of Marketing Science. 2020; 48(1):24-42.
[16]
Rane NL, Paramesha M, Choudhary SP, Rane J. Artificial intelligence, machine learning, and deep learning for advanced business strategies: a review. Partners Universal International Innovation Journal. 2024; 2(3):147-71.
[17]
Russell S. Artificial intelligence and the problem of control. Perspectives on Digital Humanism. 2022; 19:1-322.
[18]
Shi P, Yan B. A survey on intelligent control for multiagent systems. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2020; 51(1):161-75.
[19]
Tirkkonen T. Improving customer experience with artificial intelligence, data analysis, and automation in azets. Master’s Thesis, Haaga-Helia University of Applied Sciences. 2021.
[20]
Joshi S. Review of autonomous and collaborative agentic AI and multi-agent systems for enterprise applications. International Journal of Innovative Research in Engineering and Management. 2025; 12(3):65-76.
[21]
De AK, Hernandez-garcia J, Holland G, Sutton R. Multi-step reinforcement learning: a unifying algorithm. In proceedings of the AAAI conference on artificial intelligence 2018 (pp. 2902-9). AAAI.
[22]
Martinez EC, Somaglia OA. Reinforcement learning applications to process control and optimization. In intelligent systems 2018. CRC Press.
[23]
Lecun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553):436-44.
[24]
Iansiti M, Lakhani KR. Competing in the age of AI: strategy and leadership when algorithms and networks run the world. Harvard Business Press; 2020.
[25]
Agbolade AR, Efanga UO. Customer experience management (CXM) within SMES in Derby, UK: strategic importance evaluation. Responsible Consumption, Production and Accounting in Emerging Economies. 2024:1603-19.
[26]
Wirtz J, Kowalkowski C, Jaakkola E, Holmlund M, Ulaga W, Ahmed T. Customer experience management in B2B markets: CXM value propositions and archetypical CXM strategies. Journal of Business Research. 2025; 189:115165.
[27]
Wetzels RW, Wetzels M. There is a secret to success: linking customer experience management practices to profitability. Journal of Retailing and Consumer Services. 2023; 73:103338.
[28]
Adekunle BI, Chukwuma-eke EC, Balogun ED, Ogunsola KO. Improving customer retention through machine learning: a predictive approach to churn prevention and engagement strategies. International Journal of Scientific Research in Computer Science, Engineering and Information Technology. 2023; 9(4):507-23.
[29]
Ghosh S, Ness S, Salunkhe S. The role of AI enabled chatbots in omnichannel customer service. Journal of Engineering Research and Reports. 2024; 26(6):327-45.
[30]
Dogiparthi LN. Transformative multi-agent ai framework for precision sentiment response generation: advancing real-time customer engagement through large language models. 2025; 14(6):15004-11.
[31]
Wang WM, Wang JW, Barenji AV, Li Z, Tsui E. Modeling of individual customer delivery satisfaction: an autoML and multi-agent system approach. Industrial Management & Data Systems. 2019; 119(4):840-66.
[32]
Chowhan GR. AI-powered virtual agents in CRM: revolutionizing customer interaction and service automation. Journal of Computer Science and Technology Studies. 2025; 7(3):245-52.
[33]
Amine BM, Mohamed S. Intelligent agent systems: evolving decision-making models and applications. In Mediterranean smart cities conference (MSCC) 2024 (pp. 1-5). IEEE.
[34]
Schmidt LM, Brosig J, Plinge A, Eskofier BM, Mutschler C. An introduction to multi-agent reinforcement learning and review of its application to autonomous mobility. In IEEE 25th international conference on intelligent transportation systems (ITSC) 2022 (pp. 1342-9). IEEE.
[35]
Zhang S, Jia R, Li Z. Agentic AI across domains: a comprehensive review of capabilities, applications, and future directions. Journal of Computing Innovations and Applications. 2024; 2(1):86-98.
[36]
Zhu K, Du H, Hong Z, Yang X, Guo S, Wang DZ, et al. Multiagentbench: evaluating the collaboration and competition of llm agents. In proceedings of the 63rd annual meeting of the association for computational linguistics. 2025 (pp. 8580-622).
[37]
Wu Z, Ito T. The hidden strength of disagreement: Unraveling the consensus-diversity tradeoff in adaptive multi-agent systems. In proceedings of the 2025 conference on empirical methods in natural language processing 2025 (pp. 15288-308).
[38]
Voudouris C. Developing an autonomic strategy and business architecture. In autonomic business transformation: a guide to AI agents for practitioners and executives 2025 (pp. 93-106). Cham: Springer Nature Switzerland.
[39]
Benkhayat A, Chiadmi MS, Tkiouat M. Strategic business-IT alignment: a multi-agent systems approach. Journal of Information Systems Engineering and Management. 2024;9(3):1-30.
[40]
Wu X, Liang L, Jia Y, Wen W. Multi-agent collaboration for autonomous systems based on implicit strategy prediction and prioritization. In 10th international conference on computer and communications (ICCC) 2024 (pp. 2047-52). IEEE.
[41]
Glory DK, Ali H, Hyekonni BN. Rise of Ai-powered personalization: how brands are redefining customer experience in 2025. Arabian Journal of Business and Management Review (Kuwait Chapter). 2025; 14(3):83-6.
[42]
Kumar V, Dixit A, Javalgi RR, Dass M. Research framework, strategies, and applications of intelligent agent technologies (IATs) in marketing. Journal of the Academy of Marketing Science. 2016; 44(1):24-45.
[43]
Dodnikov R. Workflow optimization in finance using multi-agent systems. Innovative Information Technologies for Economy Digitalization (IITED). 2024(1):182-8.
[44]
Nweke IP, Ogadah CO, Koshechkin K, Oluwasegun PM. Multi-agent AI systems in healthcare: a systematic review enhancing clinical decision-making. Asian Journal of Medical Principles and Clinical Practice. 2025; 8(1):273-85.
[45]
Panigrahy S. Multi-agentic AI systems: a comprehensive framework for enterprise digital transformation. Journal of Computer Science and Technology Studies. 2025; 7(6):86-96.
[46]
Telnov YF, Kazakov VA, Danilov AV. Designing a multi-agent system for a network enterprise. Бизнес-Информатика. 2024; 18(3):70-86.
[47]
Sarin S, Singh SK, Kumar S, Goyal S, Gupta BB, Alhalabi W, et al. Unleashing the power of multi-agent reinforcement learning for algorithmic trading in the digital financial frontier and enterprise information systems. Computers, Materials & Continua. 2024; 80(2):3123-38.
[48]
Li Y, Gan Z, Zheng B. How do artificial intelligence chatbots affect customer purchase? Uncovering the dual pathways of anthropomorphism on service evaluation. Information Systems Frontiers. 2025; 27(1):283-300.
[49]
Jiang Z, Rashik M, Panchal K, Jasim M, Sarvghad A, Riahi P, et al. CommunityBots: creating and evaluating a multi-agent chatbot platform for public input elicitation. Proceedings of the ACM on Human-Computer Interaction. 2023; 7(CSCW1):1-32.
[50]
Calvaresi D, Eggenschwiler S, Mualla Y, Schumacher M, Calbimonte JP. Exploring agent-based chatbots: a systematic literature review. Journal of Ambient Intelligence and Humanized Computing. 2023; 14(8):11207-26.
[51]
Peruchini M, Da SGM, Teixeira JM. Between artificial intelligence and customer experience: a literature review on the intersection. Discover Artificial Intelligence. 2024; 4(1):1-10.
[52]
Huang MH, Rust RT. Engaged to a robot? the role of AI in service. Journal of Service Research. 2021; 24(1):30-41.
[53]
Adamopoulou E, Moussiades L. Chatbots: history, technology, and applications. Machine Learning with Applications. 2020; 2:100006.
[54]
Liu C, Jiang J, Xiong C, Yang Y, Ye J. Towards building an intelligent chatbot for customer service: learning to respond at the appropriate time. In proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining 2020 (pp. 3377-85). ACM.
[55]
Chenavaz R, Klibi W, Schlosser R. Dynamic pricing with reference price effects in integrated online and offline retailing. International Journal of Production Research. 2022; 60(19):5854-75.
[56]
Grewal D, Gauri DK, Das G, Agarwal J, Spence MT. Retailing and emergent technologies. Journal of Business Research. 2021; 134:198-202.
[57]
Vullam N, Vellela SS, Reddy V, Rao MV, SK KB. Multi-agent personalized recommendation system in e-commerce based on user. In 2nd international conference on applied artificial intelligence and computing (ICAAIC) 2023 (pp. 1194-9). IEEE.
[58]
Ricci F. Trustworthy Tourism Recommender Systems. In European conference on advances in databases and information systems 2025 (pp. 533-40). Cham: Springer Nature Switzerland.
[59]
Reka K, Raja G, Malarchelvi PDSK. AI and deep reinforcement learning for sentiment analysis of customer reviews. In web intelligence 2025 (pp. 213-21). Sage UK: London, England: SAGE Publications.
[60]
Wang Y, Wang Y, Tian F, Ma J, Jin Q. Intelligent games meeting with multi-agent deep reinforcement learning: a comprehensive review. Artificial Intelligence Review. 2025; 58(6):1-53.
[61]
Chen P, Zhang S, Han B. Comm: collaborative multi-agent, multi-reasoning-path prompting for complex problem solving. In findings of the association for computational linguistics: NAACL 2024 (pp. 1720-38). Association for Computational Linguistics.
[62]
Lander SE. Issues in multiagent design systems. IEEE expert. 2002 ;12(2):18-26.
[63]
Kalyuzhnaya A, Mityagin S, Lutsenko E, Getmanov A, Aksenkin Y, Fatkhiev K, et al. LLM agents for smart city management: enhancing decision support through multi-agent AI systems. Smart Cities. 2025; 8(1):1-33.
[64]
Kumar D, Jain B. Multi-agent retrieval-augmented generation for enhancing answer generation and knowledge retrieval. In EPIA conference on artificial intelligence 2025 (pp. 289-302). Cham: Springer Nature Switzerland.
[65]
Hayashi Y. Decentralized Belief Propagation in LLM Agents: A Brain-Inspired Approach to AI Safety Analysis. In international conference on neural information processing 2025 (pp. 537-50). Singapore: Springer Nature Singapore.
[66]
Fnu H, Kaushik K, Gaur P, Saratchandran DV, Thapliyal AG, Sidhu KS, et al. Multi-agent systems for collaborative financial decision-making over distributed network architectures. In 3rd international conference on advancement in computation & computer technologies (InCACCT) 2025 (pp. 939-44). IEEE.
[67]
Kumar SN. Multi-agent AI systems in finance: models, applications, and challenges. International Journal of Advanced Research in Computer Science & Technology (IJARCST). 2025; 8(1):11555-73.
[68]
Pajak E, Bahamdan A, Hellgardt K, Del río-chanona A. Multi-agent LLMs for automating sustainable operational decision-making. Systems and Control Transactions. 2025: 1824-9.
[69]
Mascardi V, Weyns D. Engineering multi-agent systems Anno 2025. In international workshop on engineering multi-agent systems 2018 (pp. 3-16). Cham: Springer International Publishing.
[70]
Zhang K, Yu X, Peng H, Yang Z, Tian Y, Jin H, et al. Towards efficient optimization of multi-agent social simulation via large language models. International Journal of Machine Learning and Cybernetics. 2026; 17(1):1.
[71]
Jimenez-romero C, Yegenoglu A, Blum C. Multi-agent systems powered by large language models: applications in swarm intelligence. Frontiers in Artificial Intelligence. 2025; 8:1-23.
[72]
Feng J, Li H, Huang M, Liu S, Ou W, Wang Z, et al. Learning to collaborate: multi-scenario ranking via multi-agent reinforcement learning. In Proceedings of the 2018 World Wide Web Conference 2018 (pp. 1939-48). ACM.
[73]
Adeyinka TI, Adeyinka KI. Intelligent, autonomous, and multi-agents. In humans and generative AI tools for collaborative intelligence 2025 (pp. 301-26). IGI Global Scientific Publishing.
[74]
Kosaraju D. Ai and multi-agent systems: collaboration and competition in autonomous environments. International Journal of Research. 2023;10(12):883-8.
[75]
Khan AN, Hui Z, Khan NA. How AI chatbots reinforce green environments to shape customer satisfaction and loyalty. International Journal of Contemporary Hospitality Management. 2026:1-9.
[76]
Baker B, Mills KA, Mcdonald P, Wang L. AI, concepts of intelligence, and chatbots: the “figure of man,” the rise of emotion, and future visions of education. Teachers College Record. 2023; 125(6):60-84.
[77]
Shunmugasundaram D. Customer experience management in age of AI: strategies for personalization and loyalty. International Conference on Pervasive Computational Technologies (ICPCT) 2025 (pp. 402-5). IEEE.
[78]
Guendouz T. Artificial intelligence-powered customer experience management (moving from mass to hyper-personalization in light of relationship marketing). International Journal for Scientific Research. 2024; 3(6):247-306.
[79]
Jordan LA. Customer experience management: opportunities, challenges and trends. Customer Experience Management in the Caribbean: Concepts, Case Studies and Challenges. 2024:1-12.
[80]
Doughman E, Dwairi H, Alahmadi KH, Bawaneh S. AI-driven automation for enhanced customer experience management in Saudi Arabia. International Journal of Open Problems in Computer Science. 2024; 17(3):26-32.
[81]
Berezin S. Explainable AI in customer experience management: personalization algorithms in CRM systems. The American Journal of Engineering and Technology. 2025; 7(04):57-64.
[82]
Kacar M. Application of AI in customer experience management. In marketing and sales automation: basics, implementation, and applications 2023 (pp. 409-30). Cham: Springer International Publishing.
[83]
Hamilton S. Deep learning computer vision algorithms, customer engagement tools, and virtual marketplace dynamics data in the metaverse economy. Journal of Self-Governance and Management Economics. 2022; 10(2):37-51.
[84]
Watson R. The virtual economy of the metaverse: computer vision and deep learning algorithms, customer engagement tools, and behavioral predictive analytics. Linguistic and Philosophical Investigations. 2022; 21:41-56.
[85]
Vom BJ, Hevner A, Maedche A. Introduction to design science research. In design science research cases 2020 (pp. 1-13). Cham: Springer International Publishing.
[86]
Venable JR, Pries-heje J, Baskerville RL. Choosing a design science research methodology. ACIS Proceedings 2017 (pp. 1-11). Association for Information Systems.
[87]
Snyder H. Literature review as a research methodology: an overview and guidelines. Journal of Business Research. 2019; 104:333-9.
[88]
Wooldridge M. An introduction to multiagent systems. John wiley & Sons; 2009.
[89]
Shoham Y, Leyton-brown K. Multiagent systems: algorithmic, game-theoretic, and logical foundations. Cambridge University Press; 2008.
[90]
Seminck O. Conversational AI: dialogue systems, conversational agents, and chatbots by Michael McTear. Association for Computational Linguistics. 2023; 49(1):257–9.
[91]
McTear M. Conversational ai: dialogue systems, conversational agents, and chatbots. Springer Nature; 2022.
[92]
Khajvandi K. AI-driven transformation: exploring the impact of generative AI on customer success management. Doctoral Dissertation, Westcliff University. 2025.
[93]
Pissarra C, Gomes JV, Romão M. Critical success factors in implementing a CRM solution: a case study. International Journal of Electronic Customer Relationship Management. 2025; 15(1-2):40-72.
[94]
Kotler P, Pfoertsch W, Sponholz U. Rethinking operative marketing: the H2H process. In H2H marketing: the genesis of human-to-human marketing 2020 (pp. 157-216). Cham: Springer International Publishing.
[95]
Kim I, Lee M, Choi Y. Building a framework for comprehensive CXM: opportunities and challenges for web-based services. In proceedings of the extended abstracts of the chi conference on human factors in computing systems 2025 (pp. 1-9). ACM.
[96]
Tembhare V, Talera N, Khan MS. CXM Technologies for smart destinations: enhancing tourists' experiences and influx. In 4th international conference on technological advancements in computational sciences (ICTACS) 2024 (pp. 1910-16). IEEE.
[97]
Filippou S, Tsiartas A, Hadjineophytou P, Christofides S, Malialis K, Panayiotou CG. Improving customer experience in call centers with intelligent customer-agent pairing. In IFIP international conference on artificial intelligence applications and innovations 2023 (pp. 214-24). Cham: Springer Nature Switzerland.
[98]
Sun Z, Lau SK. Customer experience management in e-services. In E-service intelligence: methodologies, technologies and applications 2007 (pp. 365-88). Berlin, Heidelberg: Springer Berlin Heidelberg.
[99]
Blümel J, Jha G. Designing a conversational AI agent: framework combining customer experience management, personalization, and AI in service techniques. Proceedings of the 56th Hawaii International Conference on System Sciences 2023 (pp. 1397-1406).
[100]
Khan HA. Innovative services, processes and product design crucial for enhancing customer experience. In marketing and design in the service sector: enhancing customer experience 2024 (pp. 63-81). Emerald Publishing Limited.
[101]
Kolp M, Tung DT, Faulkner S, Hang HTT. Architectural styles and patterns for multi-agent systems. In design of intelligent multi-agent systems: human-centredness, architectures, learning and adaptation 2004 (pp. 103-32). Berlin, Heidelberg: Springer Berlin Heidelberg.
[102]
Zhao Y, Wu J, Wang X, Tang W, Wang D, De RM. Let me do it for you: towards LLM empowered recommendation via tool learning. In proceedings of the 47th international conference on research and development in information retrieval 2024 (pp. 1796-806). ACM.