用可演化原子记忆提升推荐系统对用户兴趣的细粒度追踪能力
AtomRec: Evolving Atomic Memory for Agentic Recommendation
- 将用户和物品记忆拆分为结构化原子单元，动态更新历史偏好
- 在四个数据集上平均性能比顶尖模型高8.5%以上
- 适合需要解释性推荐与长期兴趣建模的研究者和工程师
基于大语言模型的智能推荐系统依赖语义记忆实现基于证据的推荐。但现有记忆机制常将用户与物品信息压缩为粗略摘要，并通过标量协同链接关联，难以保留细粒度偏好阶段或在兴趣演变时检索可解释证据。本文提出 extsc{AtomRec}，一种具备可演化原子协同记忆的智能推荐系统。该系统将用户与物品记忆表示为结构化的原子单元，构建跨相关记忆的语义链接，并在新交互到来时动态演化相关历史字段。推荐过程中，系统通过多跳证据路径而非孤立邻居摘要进行检索，使协同信号支持有依据的排序。在四个公开基准测试上， extsc{AtomRec} 持续优于当前最先进的智能推荐与记忆增强基线模型，各项指标平均相对提升约8.5%。
原文摘要 · Abstract (English)
Agentic recommender systems use large language models to maintain semantic memory and support evidence-aware recommendation. However, existing memory mechanisms often compress user and item information into coarse summaries and connect them with scalar collaborative links, making it difficult to preserve fine-grained preference stages or retrieve interpretable evidence as user interests evolve. We propose \textsc{AtomRec}, an agentic recommender with evolving atomic collaborative memory. \textsc{AtomRec} represents user and item memories as structured atomic units, builds semantic links across related memories, and evolves related historical fields when new interactions arrive. During recommendation, it retrieves linked memories as multi-hop evidence paths rather than isolated neighbor summaries, allowing collaborative signals to support grounded ranking. Experiments on four public benchmarks show that \textsc{AtomRec} consistently outperforms state-of-the-art agentic and memory-augmented baselines, with around 8.5\% average relative improvement across metrics.
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。