{"ID":2855121,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.13371","arxiv_id":"2510.13371","title":"MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation","abstract":"Recent attempts to integrate large language models (LLMs) into recommender systems have gained momentum, but most remain limited to simple text generation or static prompt-based inference, failing to capture the complexity of user preferences and real-world interactions. This study proposes the Multi-Aspect Driven LLM Agent MADRec, an autonomous LLM-based recommender that constructs user and item profiles by unsupervised extraction of multi-aspect information from reviews and performs direct recommendation, sequential recommendation, and explanation generation. MADRec generates structured profiles via aspect-category-based summarization and applies Re-Ranking to construct high-density inputs. When the ground-truth item is missing from the output, the Self-Feedback mechanism dynamically adjusts the inference criteria. Experiments across multiple domains show that MADRec outperforms traditional and LLM-based baselines in both precision and explainability, with human evaluation further confirming the persuasiveness of the generated explanations.","short_abstract":"Recent attempts to integrate large language models (LLMs) into recommender systems have gained momentum, but most remain limited to simple text generation or static prompt-based inference, failing to capture the complexity of user preferences and real-world interactions. This study proposes the Multi-Aspect Driven LLM...","url_abs":"https://arxiv.org/abs/2510.13371","url_pdf":"https://arxiv.org/pdf/2510.13371v1","authors":"[\"Jiin Park\",\"Misuk Kim\"]","published":"2025-10-15T10:03:29Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}