Agentic Recommender Systems

Recommender systems are entering a new era. As large language models and agent-based AI reshape what's possible, recommendation is no longer just a prediction problem: it's becoming a collaborative process where intelligent agents reason, communicate, coordinate, and adapt to ever-changing user needs.

Agentic Recommender Systems is a field that is exciting but still fragmented. Spanning recommender systems, LLMs, multi-agent systems, software engineering, and human-computer interaction, this book offers researchers, students, and practitioners a much-needed shared vocabulary and conceptual foundation. It moves from first principles to the frontier: grounding readers in how agentic approaches differ from traditional recommendation pipelines, proposing a general framework for reasoning about multi-agent recommendation, and tackling the open challenge of evaluation: datasets, metrics, baselines, and the limits of current methods. Along the way, real-world applications, architectural patterns, and the fast-growing ecosystem of agent frameworks and orchestration tools bring theory into practical focus.

Rather than claiming to have the final word on a still-maturing field, this book is designed as a resource to help readers navigate preference elicitation, continual user modeling, multi-agent coordination, and the broader implications of increasingly autonomous recommendation systems. Whether you're a graduate student entering the field, a researcher pushing its boundaries, or a practitioner building the next generation of intelligent recommendation technology, this book provides the coherent, comprehensive starting point the field has been missing.

First unified framework connecting recommender systems, LLMs, and multi-agent AI into one coherent field Bridges theory and practice with real architectures, applications, and evaluation methods Serves as a launchpad for research and practice in a fast-moving, still-undefined frontier field

Autorentext

Ivens da Silva Portugal is a Postdoctoral Scholar at the University of Waterloo.

Paulo Alencar is Research/Adjunct Professor with the David R. Cheriton School of Computer Science, University of Waterloo, and the Associate Director of the Computer Systems Group (CSG). He has published more than 300 refereed publications and has participated in program committees of numerous highly-regarded conferences and workshops. His current research interests include information technology and software engineering, with a focus on high-level software architectures, design, components and their interfaces, software frameworks and application families, software processes, automated and intelligent workflows, knowledge graphs, evolution, web-based approaches and applications, open and big data applications, context-aware and event-based systems, software agents, machine learning, cognitive chatbots, artificial intelligence (e.g., LLMs, generative AI, agentic software), and formal methods. He has been a Principal Investigator and a Co-Principal Investigator in projects supported by NSERC, ORF-RE, IBM, SAP, CITO, CSER, and Bell, and funding agencies in Canada USA, Brazil, Germany, and Argentina. He is a member of the Association of Computing Machinery (ACM), the Association for the Advancement of Artificial Intelligence (AAAI), Waterloo Water Institute (A part of the Global Water Futures initiative), and Waterloo Artificial Intelligence Institute. He has received international research awards from organizations, such as Compaq and IBM.

Donald Cowan is Distinguished Professor Emeritus in computer science with the University of Waterloo and the Director of the Computer Systems Group. He has contributed to computer science in computer science, software engineering, applied machine learning, and complex applications. He is the author, co-author, and editor of more than 300 refereed articles and 17 books in computer / communications, software engineering, education, environmental information systems, and mathematics. He has supervised more than 120 graduate students and postdoctoral fellows. His group has developed more than 80 web-based and mobile software systems for many applications in volunteerism, environment, socioeconomic development, tourism, population health, aboriginal affairs, arts and culture, and built heritage. The University of Waterloo recognized his contributions to the development of graduate students by presenting him with the Award of Excellence in Graduate Supervision. He was recognized for his research and support of the development of computer science in Brazil by being awarded the National Order of Scientific Merit (Grand Cross), the country's highest civilian scientific honor, by the President of Brazil. In 2009, he received the Waterloo Award, the City of Waterloo's highest civic honor, for his contributions to the City of Waterloo. In 2010, he was a Distinguished Scientist by the Association for Computing Machinery. He received a Doctor of Science degree (Hons.) in computer science and software engineering from the University of Guelph, in 2011.

Inhalt

.- Foundations.
.- Methods: Design and Implementation.
.- Methods: Evaluation.
.- Applications: Use Cases.
.- Applications: A Description of Current Agentic RS Variations.
.- Advanced Topics: Emerging Technologies.
.- Advanced Topics: Leading-Edge Areas.
.- Advanced Topics: Challenges.
.- Conclusion and Future Work.