Year: 2026
Type: preprint
Abstract: Recommender systems are essential to realworld online services due to their substantial business value. Increasingly, large language models (LLMs) have been adopted for recommendation tasks, owing to their strong reasoning capabilities and their effectiveness in handling cold-start items. A large body of work has sought to adapt retrieval-augmented generation (RAG) for LLM-based recommender systems by retrieving information from external databases and integrating it into the LLM's input to improve recommendation quality. Despite the rapid growth of the field, existing studies lack a clear taxonomy and a dedicated review of RAG methods for LLM-based recommender systems. To fill this gap, we present the first survey on this topic. First, we review the types of information used in LLM-based recommender systems, including target-user information and external databases for retrieval. Second, we characterize the design space of RAG for LLM-based recommender systems by outlining the key design choices at each stage of the pipeline: (1) retrieval, (2) augmentation, and (3) generation. Lastly, we discuss open questions for future research.
Source: HAL
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7149889488