# MemRerank: Preference Memory for Personalized Product Reranking

arXiv: https://arxiv.org/abs/2603.29247 · HTML: https://mlsanity.com/paper/2603.29247/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [Memento: Fine-tuning LLM Agents without Fine-tuning LLMs](https://mlsanity.com/paper/2508.16153/) (2025)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy](https://mlsanity.com/paper/2406.11678/) (2024)
- [Active Sampling for Pairwise Comparisons via Approximate Message Passing and Information Gain Maximization](https://mlsanity.com/paper/2004.05691/) (2020)
- [A Zero Attention Model for Personalized Product Search](https://mlsanity.com/paper/1908.11322/) (2019)
- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [Memory Assisted LLM for Personalized Recommendation System](https://mlsanity.com/paper/2505.03824/) (2025)
- [MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs](https://mlsanity.com/paper/2510.14629/) (2025)
- [Sparse Pairwise Re-ranking with Pre-trained Transformers](https://mlsanity.com/paper/2207.04470/) (2022)
- [Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search](https://mlsanity.com/paper/2004.09424/) (2020)
- [Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers](https://mlsanity.com/paper/2507.06223/) (2025)
- [Harnessing Multimodal Large Language Models for Personalized Product Search with Query-aware Refinement](https://mlsanity.com/paper/2509.18682/) (2025)

## Built on by (most cited first, 2 of 2)

- [Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning](https://mlsanity.com/paper/2608.09507/) (2026)
- [A Controlled Audit of Personal AI Memory for Rating Prediction](https://mlsanity.com/paper/2610.02764/) (2026)

## Abstract (arXiv)

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 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 +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.