MemRerank: Preference Memory for Personalized Product Reranking
This addresses the challenge of personalized product recommendations in e-commerce systems, offering an incremental improvement over existing memory-based methods.
The paper tackled the problem of ineffective personalization in LLM-based shopping agents due to noisy and lengthy purchase histories by proposing MemRerank, a preference memory framework that distills history into concise signals for product reranking, resulting in up to +10.61 absolute points improvement in 1-in-5 accuracy.
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.