用记忆提取器精炼用户购物历史，提升商品重排序准确率
MemRerank: Preference Memory for Personalized Product Reranking
- 将用户历史购物数据提炼为与查询无关的偏好信号
- 在1选5任务中提升10.61%准确率，优于原始历史和现有方法
- 适合构建智能电商代理的个性化推荐系统
基于大模型的购物代理越来越依赖长期购买历史和多轮交互实现个性化，但直接将原始历史拼接到提示中往往因噪声、长度和相关性不匹配而效果不佳。我们提出MemRerank，一种偏好记忆框架，将用户购买历史提炼为简洁、与查询无关的信号，用于个性化商品重排序。为研究该问题，我们构建了一个端到端的基准和评估框架，核心是基于大模型的1选5选择任务，衡量记忆质量和下游重排序效用。我们进一步使用强化学习训练记忆提取器，以下游重排序性能作为监督信号。在两个基于LLM的重排序器上的实验表明，MemRerank始终优于无记忆、原始历史及现成记忆基线，在1选5准确率上最高提升10.61个百分点。结果表明，显式的偏好记忆是智能电商代理个性化中的实用且有效的组件。
原文摘要 · Abstract (English)
LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmark and evaluation framework centered on an LLM-based \textbf{1-in-5} selection task, which measures both memory quality and downstream reranking utility. We further train the memory extractor with reinforcement learning (RL), using downstream reranking performance as supervision. Experiments with two LLM-based rerankers show that MemRerank consistently outperforms no-memory, raw-history, and off-the-shelf memory baselines, yielding up to \textbf{+10.61} absolute points in 1-in-5 accuracy. These results suggest that explicit preference memory is a practical and effective building block for personalization in agentic e-commerce systems.
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。