RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce

arXiv:2609.38974v1 Announce Type: new Abstract: Large language models are reshaping ecommerce from static recommenders into interactive shopping assistants, yet real-world shopping requires session-level decision support: users reveal and revise constraints, coordinate multiple goals, and expect product-grounded recommendations over a full conversation. Existing benchmarks are mostly outcome-oriented or execution-oriented, leaving this evolving decision process under-evaluated. We introduce REALWORLDSHOP, a benchmark built on 3.28M grounded products, structured shopping episodes, a profile-grounded and actioncontrolled user simulator, and role-play evaluation. Our analysis shows that current systems produce locally plausible responses but struggle with state tracking, constraint updating, and grounded convergence, especially under ambiguous intent, bundle, and multi-intent scenarios. We further propose REALSHOP_AGENT, an executable session-control framework with explicit state management, shopping-flow control, catalog-grounded retrieval, and runtime guards. Experiments show that REALSHOP_AGENT consistently outperforms strong baselines on REALWORLDSHOP.

Related

• MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation
• E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios
• DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents

Source: arXiv cs.AI | 2026-10-01