Abstract
Personalization is becoming a core capability of modern AI systems. It enables systems to adapt their responses and behaviors according to individual users' preferences, contexts, and goals. Recent research has focused on Retrieval-Augmented Generation (RAG) and its development toward more advanced agent-based frameworks to improve user satisfaction in personalized settings. In this tutorial, we provide a systematic overview of how personalization can be incorporated into the three main stages of RAG: pre-retrieval, retrieval, and generation. We then extend the discussion to personalized LLM-based agents, which build on RAG by adding agent capabilities such as user understanding, personalized planning and execution, and adaptive response generation. For both RAG-based and agent-based approaches, we present clear definitions, review recent research, and summarize commonly used datasets and evaluation metrics. We also discuss key challenges, current limitations, and potential future research directions. An updated list of related papers and resources is available at our GitHub repository. https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent. Further updates for this tutorial will be uploaded on the homepage. https://applied-machine-learning-lab.github.io/SIGIR2026_PRAG_Tutorial.
Funding Information
  • National Natural Science Foundation of China (62502404)
  • Hong Kong Research Grants Council Research Impact Fund (R1015-23)
  • Hong Kong Research Grants Council Collaborative Research Fund (No.C1043-24GF)
  • Hong Kong Research Grants Council General Research Fund (11218325)
  • Institute of Digital Medicine of City University of Hong Kong (9229503)
  • Huawei (Huawei Innovation Research Program) (NAN)