Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions

2026-02-26

AI Summary

This work proposes a unified framework for personalized large language model (LLM) agents to enhance their adaptability to individual user needs and behavioral continuity in long-term human–agent interactions. Centered on four core components—user modeling, memory, planning, and execution—the framework integrates techniques for representing, propagating, and leveraging user signals. Through a systematic literature review and architectural analysis, the study establishes the first capability-oriented taxonomy that elucidates cross-component coordination mechanisms and critical design trade-offs. By offering a structured pathway for understanding personalized agent behavior, this framework lays both a theoretical foundation and an evaluation benchmark for developing next-generation intelligent assistants that are better aligned with users and amenable to scalable deployment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

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

Abstract

Large language models have enabled agents that reason, plan, and interact with tools and environments to accomplish complex tasks. As these agents operate over extended interaction horizons, their effectiveness increasingly depends on adapting behavior to individual users and maintaining continuity across time, giving rise to personalized LLM-powered agents. In such long-term, user-dependent settings, personalization permeates the entire decision pipeline rather than remaining confined to surface-level generation. This survey provides a capability-oriented review of personalized LLM-powered agents. We organize the literature around four interdependent components: profile modeling, memory, planning, and action execution. Using this taxonomy, we synthesize representative methods and analyze how user signals are represented, propagated, and utilized, highlighting cross-component interactions and recurring design trade-offs. We further examine evaluation metrics and benchmarks tailored to personalized agents, summarize application scenarios spanning general assistance to specialized domains, and outline future directions for research and deployment. By offering a structured framework for understanding and designing personalized LLM-powered agents, this survey charts a roadmap toward more user-aligned, adaptive, robust, and deployable agentic systems, accelerating progress from prototype personalization to scalable real-world assistants.

Problem

• personalized agents
• LLM-powered agents
• user adaptation
• long-term interaction
• behavior continuity

Innovation

• personalized LLM agents
• profile modeling
• memory mechanisms
• adaptive planning
• user-aligned agentic systems