MemRerank framework enhances LLM shopping agents with preference memory

Researchers have developed MemRerank, a novel framework designed to improve personalized product reranking in LLM-based shopping agents. This system distills a user's extensive purchase history into concise, query-independent signals, addressing issues of noise and relevance mismatch common with raw history. MemRerank utilizes a memory extractor trained with reinforcement learning, demonstrating significant improvements in accuracy, with experiments showing up to a 10.61 absolute point increase in 1-in-5 selection tasks compared to baseline methods. AI

IMPACT Improves personalization in e-commerce LLM agents by refining how purchase history is utilized.

RANK_REASON Academic paper detailing a new framework and benchmark for LLM-based personalization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• MemRerank
• ScienceCast
• Zhiyuan Peng

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →