当记忆获取梯度：面向智能体推荐系统的协同向量记忆
When Memory Takes Gradients: Collaborative Vector Memory for Agentic Recommender Systems
- Shenzhen Technology University（深圳技术大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对智能体推荐系统中文本记忆的局限，提出CoVeMem协同向量记忆方法，在四个推荐基准上多数指标优于现有文本记忆智能体，无需额外LLM调用即可利用完整交互历史优化模型。
AI中文摘要：
智能体推荐系统将大型语言模型（LLM）的每一次决策都建立在持久的用户记忆基础上，而现有智能体的记忆是文本：由进一步的LLM调用编写和维护的叙述内容。文本在两方面限制了这种记忆：它一次只能通过重写进行更新，因此利用完整的交互历史成本极高；且整个目录上的分级相似度这类协同证据，在转换为句子后无法保留。我们提出CoVeMem（Collaborative Vector Memory，协同向量记忆），它将智能体记忆的协同核心向量化。冻结的LightGCN用户和物品状态构成记忆库；在每一次决策时，候选集自身会检索最相关的历史状态，这些状态会作为软标记与轻量文本简介一同进入LLM的上下文。与物品语义锚点的对比对齐，再加上带掩码候选的列表式协同训练，使模型学会读取这些状态并通过它们进行排序；逐点的是/否读出器会对每个候选进行评分。在四个基于指令的推荐基准上，CoVeMem在20个指标单元中的19个上与最强的协同文本记忆智能体表现相当或更优，且除了共享的静态简介外，记忆维护不需要额外的LLM调用，而文本记忆则需要每次交互都调用LLM。现在记忆可以获取梯度：原本文本无法触及的完整交互历史，现在可作为训练数据用于优化智能体的记忆内容以及读取记忆的方式。
英文摘要：
Agentic recommender systems ground each decision of a large language model (LLM) in a persistent memory of the user, and in existing agents that memory is text: a narrative written and maintained by further LLM calls. Text limits this memory in two ways. It is updated one rewrite at a time, so exploiting the full interaction history is prohibitively expensive; and collaborative evidence, graded similarity over an entire catalog, does not survive translation into sentences. We propose CoVeMem (Collaborative Vector Memory), which vectorizes the collaborative core of the agent's memory. Frozen LightGCN user and item states form the memory bank; at each decision, the candidate set itself retrieves the most relevant historical states, which enter the LLM's context as soft tokens alongside a light textual profile. Contrastive alignment to item-semantic anchors, followed by listwise co-training with masked candidates, teaches the model to read these states and to rank through them; a pointwise yes/no readout scores each candidate. Across four instruction-grounded recommendation benchmarks, CoVeMem matches or exceeds the strongest collaborative text-memory agent on 19 of 20 metric cells while requiring zero additional LLM calls for memory maintenance beyond the shared static profile, against per-interaction calls for text memory. The memory now takes gradients: the full interaction history, out of reach for text, becomes available as training data for what the agent remembers and for how it reads what it remembers.
