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.

翻译：近期将大语言模型（LLM）整合到推荐系统中的尝试日益增多，但多数方法仍局限于简单的文本生成或基于静态提示的推理，未能有效捕捉用户偏好的复杂性和现实世界中的交互动态。本研究提出多维度驱动的大语言模型智能体MADRec，这是一种基于LLM的自主推荐系统，它通过无监督地从评论中提取多维度信息来构建用户与物品画像，并执行直接推荐、序列推荐及解释生成任务。MADRec通过基于维度类别的摘要生成结构化画像，并应用重排序技术构建高密度输入。当输出结果中缺失真实物品时，其自反馈机制能动态调整推理标准。跨多个领域的实验表明，MADRec在推荐准确性和可解释性方面均优于传统方法及基于LLM的基线模型，人工评估进一步证实了其生成解释的说服力。