A survey published on July 7, 2026 proposes classifying recommender systems with LLM-based agents by their level of autonomy.
Published on July 7, 2026, the survey examines large language model-based agents in recommender systems and proposes a taxonomy organized by autonomy level. It distinguishes three paradigms: agent-assisted recommendation, the agent as recommender, and the agent as user simulator.
The classification is intended to help engineers distinguish design patterns for incorporating agents into recommender systems. To consult and verify the details, search for the original publication by title and check its scope, definitions, and descriptions of each paradigm. If you use AI to study or apply the material, do not submit sensitive organizational data without first applying your organization’s protection policies.