Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles

2025-10-09

AI Summary

Existing LLM agents struggle with context integration and user modeling in long-term personalized interactions, lacking sustainable mechanisms for incremental personalization. This paper proposes a unified personalization framework grounded in persistent memory and an evolvable user profile, integrating retrieval-augmented generation (RAG), multi-source dynamic retrieval, self-verifying response generation, and multi-agent coordinated orchestration to jointly model and incrementally update user data and dialogue history. Its key innovations include: (1) a representation of the user profile that dynamically evolves over time, and (2) a closed-loop technical pipeline coupling memory, retrieval, and verification. Evaluated on three public benchmarks, the method significantly improves retrieval accuracy and response correctness (BertScore +12.3%). A five-day user study further confirms substantially enhanced subjective personalization perception (p < 0.01). The framework establishes a scalable technical paradigm for long-term adaptive LLM agents.

Technology Category

• Multiagent Systems: Adversarial Agents
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Life-Long and Continual Learning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly 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.

Problem

• Enabling personalized long-term interactions in LLM-based agents
• Addressing limitations in combining contextual information with user data
• Developing technical implementation for adaptive user-centered AI agents

Innovation

• Integrates persistent memory with user profiles
• Uses dynamic coordination and self-validation mechanisms
• Combines multi-agent collaboration with multi-source retrieval