用大模型推理物品间隐含关系，提升推荐准确性与可扩展性
AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
- 大模型结合历史行为，推理物品的替代与互补关系
- 在三个生鲜数据集上实现基线工具两倍的排名性能提升
- 适合需要高精度、可扩展推荐系统的研究与应用
近期基于代理的推荐框架通过记忆机制和提示策略模拟用户行为，但面临虚构不存在物品和全量排序的挑战。此外，利用大模型常识推理捕捉物品间的隐含替代与互补关系仍属未充分探索的机遇，这类关系通常在数据集中难以被传统基于ID的推荐系统识别。本文提出新型大模型代理框架AgentDR，将大模型推理与可扩展推荐工具结合：由传统模型负责全量排序，大模型则根据个性化工具适配度融合多个推荐结果，并基于用户历史推理物品间的替代与互补关系。该设计有效缓解幻觉问题，支持大规模商品目录，通过关系推理显著提升推荐相关性。在三个公开生鲜数据集上的实验表明，该框架平均比基线工具性能提升两倍。我们还引入一种新的基于大模型的评估指标，联合衡量语义对齐与排序正确性。
原文摘要 · Abstract (English)
Recent agent-based recommendation frameworks aim to simulate user behaviors by incorporating memory mechanisms and prompting strategies, but they struggle with hallucinating non-existent items and full-catalog ranking. Besides, a largely underexplored opportunity lies in leveraging LLMs'commonsense reasoning to capture user intent through substitute and complement relationships between items, which are usually implicit in datasets and difficult for traditional ID-based recommenders to capture. In this work, we propose a novel LLM-agent framework, AgenDR, which bridges LLM reasoning with scalable recommendation tools. Our approach delegates full-ranking tasks to traditional models while utilizing LLMs to (i) integrate multiple recommendation outputs based on personalized tool suitability and (ii) reason over substitute and complement relationships grounded in user history. This design mitigates hallucination, scales to large catalogs, and enhances recommendation relevance through relational reasoning. Through extensive experiments on three public grocery datasets, we show that our framework achieves superior full-ranking performance, yielding on average a twofold improvement over its underlying tools. We also introduce a new LLM-based evaluation metric that jointly measures semantic alignment and ranking correctness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。