ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants
This addresses the need for better evaluation and training tools for LLM agents in e-commerce shopping, though it is incremental as it builds on existing agent frameworks.
The authors tackled the lack of a unified simulation environment for evaluating and training LLM-based shopping assistants by introducing ShopSimulator, a large-scale Chinese shopping environment, where they found top models achieved under 40% full-success rate and improved performance through SFT and RL training.
Large language model (LLM)-based agents are increasingly deployed in e-commerce shopping. To perform thorough, user-tailored product searches, agents should interpret personal preferences, engage in multi-turn dialogues, and ultimately retrieve and discriminate among highly similar products. However, existing research has yet to provide a unified simulation environment that consistently captures all of these aspects, and always focuses solely on evaluation benchmarks without training support. In this paper, we introduce ShopSimulator, a large-scale and challenging Chinese shopping environment. Leveraging ShopSimulator, we evaluate LLMs across diverse scenarios, finding that even the best-performing models achieve less than 40% full-success rate. Error analysis reveals that agents struggle with deep search and product selection in long trajectories, fail to balance the use of personalization cues, and to effectively engage with users. Further training exploration provides practical guidance for overcoming these weaknesses, with the combination of supervised fine-tuning (SFT) and reinforcement learning (RL) yielding significant performance improvements. Code and data will be released at https://github.com/ShopAgent-Team/ShopSimulator.