Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
Rebecca Westhäußer, Wolfgang Minker, Sebatian Zepf
TL;DR
This work defines a concrete framework to enable personalized, long-term interactions for LLM-based agents by integrating six agentic AI patterns with persistent memory and dynamic user profiles. It combines a Coordinator-Operator-Self-Validator-Response Generator workflow with memory modules (STM, summaries, LTM) and an evolving user profile to achieve adaptivity, consistency, and tailored responses, evaluated on three public datasets and a five-day pilot. Results show competitive retrieval and response quality versus a RAG baseline and reveal the user profile as a critical driver of personalization, with pilot feedback indicating perceived personalization and a need for more proactive behavior. The framework offers a practical path toward memory-driven, user-centered AI agents and highlights future work on onboarding, proactivity, and longitudinal user studies to strengthen personalization across longer interactions.
Abstract
Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM capabilities by improving context-awareness, it lacks mechanisms to combine contextual information with user-specific data. Although personalization has been studied in fields such as human-computer interaction or cognitive science, existing perspectives largely remain conceptual, with limited focus on technical implementation. To address these gaps, we build on a unified definition of personalization as a conceptual foundation to derive technical requirements for adaptive, user-centered LLM-based agents. Combined with established agentic AI patterns such as multi-agent collaboration or multi-source retrieval, we present a framework that integrates persistent memory, dynamic coordination, self-validation, and evolving user profiles to enable personalized long-term interactions. We evaluate our approach on three public datasets using metrics such as retrieval accuracy, response correctness, or BertScore. We complement these results with a five-day pilot user study providing initial insights into user feedback on perceived personalization. The study provides early indications that guide future work and highlights the potential of integrating persistent memory and user profiles to improve the adaptivity and perceived personalization of LLM-based agents.