The evolution of recommender systems has shifted preference storage from rating matrices and dense embeddings to semantic memory in the agentic era. Yet existing agents rely on isolated memory, overlooking crucial collaborative signals. Bridging this gap is hindered by the dual challenges of distilling vast graph contexts without overwhelming reasoning agents with cognitive load, and evolving the collaborative memory efficiently without incurring prohibitive computational costs. To address this, we propose MemRec, a framework that architecturally decouples reasoning from memory management to enable efficient collaborative augmentation. MemRec introduces a dedicated, cost-effective LM_Mem to manage a dynamic collaborative memory graph, serving synthesized, high-signal context to a downstream LLM_Rec. The framework operates via a practical pipeline featuring efficient retrieval and cost-effective asynchronous graph propagation that evolves memory in the background. Extensive experiments on four benchmarks demonstrate that MemRec achieves state-of-the-art performance. Furthermore, architectural analysis confirms its flexibility, establishing a new Pareto frontier that balances reasoning quality, cost, and privacy through support for diverse deployments, including local open-source models. Code:https://github.com/rutgerswiselab/memrec and Homepage: https://memrec.weixinchen.com

翻译：推荐系统的发展已从评分矩阵和稠密嵌入转向代理时代的语义记忆作为偏好存储方式。然而现有代理依赖孤立记忆，忽视了关键的协作信号。弥合这一鸿沟面临双重挑战：既要提炼海量图上下文而不使推理代理承受过高的认知负荷，又要高效演化协作记忆而不产生过高的计算成本。为此，我们提出MemRec框架，通过架构设计将推理与记忆管理解耦，以实现高效的协作增强。MemRec引入一个专用的经济型LM_Mem来管理动态协作记忆图，为下游LLM_Rec提供经过合成的高信号上下文。该框架通过实用化流程运作，具备高效检索和经济型异步图传播机制，可在后台持续演化记忆。在四个基准数据集上的大量实验表明，MemRec实现了最先进的性能。此外，架构分析证实了其灵活性：通过支持包括本地开源模型在内的多样化部署方案，MemRec建立了平衡推理质量、成本与隐私的新帕累托前沿。代码：https://github.com/rutgerswiselab/memrec 项目主页：https://memrec.weixinchen.com