Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems

2026-07-05

AI Summary

Traditional recommender systems lack autonomy and interactivity, rendering them ill-equipped to handle dynamic and complex user demands. This work proposes a unified framework centered on autonomy that, for the first time, integrates the three prevailing paradigms of agent-based recommender systems: agent-assisted recommendation, agents as recommenders, and agents as user simulators. Built upon large language models, the framework encompasses user profiling, memory mechanisms, tool invocation, and workflow optimization, while systematically articulating architectural design principles and evaluation methodologies. The study identifies critical challenges—including trajectory-level evaluation, contribution attribution, and user simulator calibration—and establishes foundational theoretical insights alongside practical evaluation guidelines. It further outlines promising future directions such as lifelong modeling, multimodal alignment, controllability, and privacy preservation.

Abstract

The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive systems that can reason, plan, and act. This survey provides a comprehensive overview of this emerging landscape by introducing a unified taxonomy grounded in the level of autonomy and three core paradigms of agentic recommender systems: agent-assisted recommendation, agent-as-recommender, and agent-as-user-simulator. The autonomy framework organizes existing methods along increasing capabilities in proactivity, context awareness, interaction flexibility, and adaptivity. Building on this framework, the survey analyzes how each paradigm adopts different agentic architectures and how agents enhance key components such as profiles, memory, tool use, workflows, and optimization mechanisms. We further examine evaluation methodologies for agentic recommendation, covering automated metrics, LLM-based judging, and simulation-based assessment, and discuss their limitations in capturing reasoning quality, user experience, and system behavior. Beyond existing evaluation protocols, we further discuss unresolved issues in evaluating agentic recommender systems, including trajectory-level assessment, agent contribution analysis, and calibration of user simulation. Lastly, the survey outlines open challenges in lifelong user modeling, contextual abstraction, multimodal alignment, controllability, trustworthiness, privacy, scalability, and efficiency. Together, these analyses establish a unified foundation for understanding the current progress of agentic recommender systems and highlight promising opportunities for developing more autonomous, reliable, and human-aligned recommendation agents.

Problem

• agentic recommender systems
• autonomy
• evaluation methodologies
• user modeling
• trustworthiness

Innovation

• Agentic Recommender Systems
• Autonomy Framework
• Agent-as-User-Simulator
• LLM-based Evaluation
• Interactive Recommendation