Shopping Companion: A Memory-Augmented LLM Agent for Real-World E-Commerce Tasks

TL;DR

This paper introduces a new benchmark and a unified memory-augmented LLM framework for e-commerce shopping tasks, improving long-term preference understanding and task performance in real-world scenarios.

Contribution

It presents a novel benchmark for long-term preference-aware shopping tasks and a unified framework that jointly handles memory retrieval and shopping assistance.

Findings

Lightweight LLM trained with our method outperforms baselines.

State-of-the-art models achieve under 70% success on the benchmark.

Our approach effectively captures user preferences over long-term interactions.

Abstract

In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budgeting, and bundle deals, where accurately capturing user preferences from long-term conversations is critical. However, two challenges hinder realizing this potential: (1) the absence of benchmarks for evaluating long-term preference-aware shopping tasks, and (2) the lack of end-to-end optimization due to existing designs that treat preference identification and shopping assistance as separate components. In this paper, we introduce a novel benchmark with a long-term memory setup, spanning two shopping tasks over 1.2 million real-world products, and propose Shopping Companion, a unified framework that jointly tackles memory retrieval and shopping assistance while supporting user intervention. To train such capabilities, we develop a dual-reward reinforcement learning strategy with tool-wise rewards to handle the sparse and discontinuous rewards inherent in multi-turn interactions. Experimental results demonstrate that even state-of-the-art models (such as GPT-5) achieve success rates under 70% on our benchmark, highlighting the significant challenges in this domain. Notably, our lightweight LLM, trained with Shopping Companion, consistently outperforms strong baselines, achieving better preference capture and task performance, which validates the effectiveness of our unified design.