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

• URL: http://arxiv.org/abs/2603.14864v1
• Date: Mon, 16 Mar 2026 06:07:52 GMT
• Title: Shopping Companion: A Memory-Augmented LLM Agent for Real-World E-Commerce Tasks
• Abstract summary: LLM agents show promise for shopping tasks such as recommendations, budgeting, and bundle deals.<n>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.<n>We propose Shopping Companion, a unified framework that jointly tackles memory retrieval and shopping assistance while supporting user intervention.
• Score: 6.67534912037121
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization [54.855135506924775]
  We introduce a two-stage multi-objective optimization framework for aligning tool-using large language models (LLMs) under competing objectives.<n>This design enables fine-grained, action-level optimization across multiple conflicting objectives.
  arXiv  Detail & Related papers  (2026-06-15T01:58:07Z)
• Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR [35.58360539504091]
  ShopTrajQA is a long-context evaluation benchmark constructed from real-world product information and simulated shopping trajectories.<n>We show that our framework achieves strong performance for ShopTrajQA and shows generalization to other complex reasoning tasks.
  arXiv  Detail & Related papers  (2026-06-06T06:22:07Z)
• Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation [59.362016745945375]
  We propose the first Tri-party LLM-agent Recommendation framework (TriRec)<n>TriRec explicitly coordinates user utility, item exposure, and platform-level fairness.<n>We show consistent gains in accuracy, fairness, and item-level utility.
  arXiv  Detail & Related papers  (2026-03-11T11:40:13Z)
• ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning [88.87305027895657]
  This work investigates Reinforcement Learning-based optimization for shopping agents in real-world scenarios.<n>Agents must simultaneously satisfy multiple interdependent objectives spanning objective metrics (product correctness), subjective qualities (persuasiveness), outcome rewards (final response quality), and process rewards (tool efficiency)<n>Experiments demonstrate that our RL-trained agent, ChatShopBuddy, consistently outperforms larger models relying on generic reasoning.
  arXiv  Detail & Related papers  (2026-03-06T09:18:51Z)
• ShoppingComp: Are LLMs Really Ready for Your Shopping Cart? [21.021833054625095]
  ShoppingComp is a challenging real-world benchmark for rigorously evaluating LLM-powered shopping agents.<n>It introduces highly complex tasks under the principle of guaranteeing real products and ensuring easy verifiability.<n>The benchmark comprises 120 tasks and 1,026 scenarios, curated by 35 experts to reflect authentic shopping needs.
  arXiv  Detail & Related papers  (2025-11-28T08:32:54Z)
• E-CARE: An Efficient LLM-based Commonsense-Augmented Framework for E-Commerce [26.230331478424517]
  We propose the Efficient Commonsense-Augmented Recommendation Enhancer (E-CARE) for e-commerce tasks.<n>During inference, models augmented with E-CARE can access commonsense reasoning with only a single LLM forward pass per query.<n>Experiments on 2 downstream tasks show an improvement of up to 12.1% on precision@5.
  arXiv  Detail & Related papers  (2025-11-06T05:57:48Z)
• ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents [21.399546417224755]
  Existing benchmarks in e-commerce primarily focus on basic user intents, such as finding or purchasing products.<n>We propose ShoppingBench, a novel end-to-end shopping benchmark designed to encompass increasingly challenging levels of grounded intent.<n>We provide a large-scale shopping sandbox that serves as an interactive simulated environment, incorporating over 2.5 million real-world products.
  arXiv  Detail & Related papers  (2025-08-06T09:51:30Z)
• Optimizing Recall or Relevance? A Multi-Task Multi-Head Approach for Item-to-Item Retrieval in Recommendation [23.61568268070558]
  We propose a Multi-Task and Multi-Head I2I retrieval model that achieves both high recall and semantic relevance.<n>We evaluate MTMH using proprietary data from a commercial platform serving billions of users and demonstrate that it can improve recall by up to 14.4% and semantic relevance by up to 56.6%.
  arXiv  Detail & Related papers  (2025-06-06T17:00:20Z)
• EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association [83.4879773429742]
  This paper defines the task of E-commerce Script Planning (EcomScript) as three sequential subtasks.<n>We propose a novel framework that enables the scalable generation of product-enriched scripts by associating products with each step.<n>We construct the very first large-scale EcomScript dataset, EcomScriptBench, which includes 605,229 scripts sourced from 2.4 million products.
  arXiv  Detail & Related papers  (2025-05-21T07:21:38Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems [67.52782366565658]
  State-of-the-art recommender systems (RSs) depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables.<n>Despite the prosperity of lightweight embedding-based RSs, a wide diversity is seen in evaluation protocols.<n>This study investigates various LERS' performance, efficiency, and cross-task transferability via a thorough benchmarking process.
  arXiv  Detail & Related papers  (2024-06-25T07:45:00Z)
• Optimizing Credit Limit Adjustments Under Adversarial Goals Using Reinforcement Learning [42.303733194571905]
  We seek to find and automatize an optimal credit card limit adjustment policy by employing reinforcement learning techniques. Our research establishes a conceptual structure for applying reinforcement learning framework to credit limit adjustment.
  arXiv  Detail & Related papers  (2023-06-27T16:10:36Z)
• ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest [60.841761065439414]
  At Pinterest, we build a single set of product embeddings called ItemSage to provide relevant recommendations in all shopping use cases. This approach has led to significant improvements in engagement and conversion metrics, while reducing both infrastructure and maintenance cost.
  arXiv  Detail & Related papers  (2022-05-24T02:28:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.