发表机构
Microsoft（微软公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对基于大语言模型的智能体在推荐系统中的局限性，提出PRTA框架，让LLM作中央规划器与多推荐模型交互，负责高级推理和个性化工具选择，传统模型进行全排序评分，设计反射机制，实验表明该框架提升了全排序推荐性能。
AI 中文摘要
尽管大语言模型（LLMs）因其强大的推理能力和广泛的世界知识，最近在推荐系统中受到关注，但基于LLM的智能体存在幻觉和上下文长度限制，不适用于全排序推荐任务。为通过架构设计而非修改LLM本身来规避这些限制，我们提出基于智能体的推荐框架PRTA，其中LLM作为中央规划器与多个推荐模型作为工具交互。LLM智能体负责高级推理和个性化工具选择，传统推荐模型进行全排序评分。为支持个性化工具选择，设计了反射机制。实验证明PRTA在提高全排序推荐性能方面优于传统推荐和基于LLM的基线。
英文摘要
Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based $\textbf{P}$ersonalized $\textbf{R}$ecommendation $\textbf{T}$ool learning via autonomous language $\textbf{A}$gents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of \modelname over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance.
Comments6 pages. Accepted by RecSys'26
