ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents
This addresses the need for better benchmarks in e-commerce for AI agents, though it is incremental as it builds on existing evaluation frameworks.
The authors tackled the problem of evaluating LLM-based agents on complex real-world shopping tasks by creating ShoppingBench, a benchmark with grounded intents like applying vouchers and managing budgets, which shows state-of-the-art agents achieve under 50% success rates. They also developed a trajectory distillation method to train a smaller agent that performs competitively with GPT-4.1.
Existing benchmarks in e-commerce primarily focus on basic user intents, such as finding or purchasing products. However, real-world users often pursue more complex goals, such as applying vouchers, managing budgets, and finding multi-products seller. To bridge this gap, we propose ShoppingBench, a novel end-to-end shopping benchmark designed to encompass increasingly challenging levels of grounded intent. Specifically, we propose a scalable framework to simulate user instructions based on various intents derived from sampled real-world products. To facilitate consistent and reliable evaluations, we provide a large-scale shopping sandbox that serves as an interactive simulated environment, incorporating over 2.5 million real-world products. Experimental results demonstrate that even state-of-the-art language agents (such as GPT-4.1) achieve absolute success rates under 50% on our benchmark tasks, highlighting the significant challenges posed by our ShoppingBench. In addition, we propose a trajectory distillation strategy and leverage supervised fine-tuning, along with reinforcement learning on synthetic trajectories, to distill the capabilities of a large language agent into a smaller one. As a result, our trained agent achieves competitive performance compared to GPT-4.1.