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

TL;DR

This paper surveys the development of personalized large language model-powered agents, focusing on core capabilities, evaluation methods, and future research directions to enhance user-specific adaptability and long-term interaction quality.

Contribution

It introduces a comprehensive taxonomy of capabilities for personalized LLM agents and analyzes existing methods, evaluation metrics, and application scenarios to guide future development.

Findings

Organized around four key capabilities: profile modeling, memory, planning, and action execution.

Highlights cross-component interactions and recurring design challenges.

Examines evaluation metrics and benchmarking paradigms for personalized agents.

Abstract

Large language models have enabled agentic systems 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 interactions, giving rise to personalized LLM-powered agents (PLAs). In such long-term, user-dependent settings, personalization permeates the entire decision pipeline rather than remaining confined to surface-level response generation. This survey provides a capability-oriented review of personalized LLM-powered agents. Existing work is organized around four interdependent capabilities: profile modeling, memory, planning, and action execution. Using this taxonomy, representative methods are synthesized and analyzed to illustrate how user signals are represented, propagated, and utilized across the agent pipeline, highlighting cross-component interactions and recurring design challenges. Evaluation metrics and benchmarking paradigms tailored to personalized agents are further examined, along with application scenarios ranging from conversational assistants to domain-specific expert systems. By clarifying the design space of personalization in agent systems, this survey provides a structured foundation for developing more user-aligned, adaptive, and deployable LLM-powered agents.