Recent advancements in instructing Large Language Models (LLMs) to utilize external tools and execute multi-step plans have significantly enhanced their ability to solve intricate tasks, ranging from mathematical problems to creative writing. Yet, there remains a notable gap in studying the capacity of LLMs in responding to personalized queries such as a recommendation request. To bridge this gap, we have designed an LLM-powered autonomous recommender agent, RecMind, which is capable of providing precise personalized recommendations through careful planning, utilizing tools for obtaining external knowledge, and leveraging individual data. We propose a novel algorithm, Self-Inspiring, to improve the planning ability of the LLM agent. At each intermediate planning step, the LLM 'self-inspires' to consider all previously explored states to plan for next step. This mechanism greatly improves the model's ability to comprehend and utilize historical planning information for recommendation. We evaluate RecMind's performance in various recommendation scenarios, including rating prediction, sequential recommendation, direct recommendation, explanation generation, and review summarization. Our experiment shows that RecMind outperforms existing zero/few-shot LLM-based recommendation methods in different recommendation tasks and achieves competitive performance to a recent model P5, which requires fully pre-train for the recommendation tasks.

翻译：近期在指导大型语言模型（LLMs）使用外部工具并执行多步规划方面取得的进展，显著提升了其解决复杂任务（从数学问题到创意写作）的能力。然而，关于LLMs应对个性化查询（如推荐请求）的能力研究仍存在明显空白。为填补这一空白，我们设计了一个由LLM驱动的自主推荐智能体RecMind，它能够通过精心规划、利用工具获取外部知识以及运用个体数据，提供精确的个性化推荐。我们提出一种新颖算法"自我启发"（Self-Inspiring），以提升LLM智能体的规划能力。在每步中间规划过程中，LLM会"自我启发"以考虑先前探索过的所有状态，从而规划下一步行动。该机制极大地增强了模型理解和利用历史规划信息进行推荐的能力。我们在多种推荐场景下评估RecMind的性能，包括评分预测、序列推荐、直接推荐、解释生成和评论摘要。实验表明，RecMind在不同推荐任务中均优于现有的基于LLM的零/少样本推荐方法，并在性能上与近期需要针对推荐任务进行完全预训练的模型P5具有竞争力。