Ecom-RLVE introduces verifiable gym for e-commerce AI agents
huggingface released ecom-rlve, a verifiable reinforcement learning environment for training e-commerce conversational agents. unlike llm-as-a-judge approaches, it uses programmatic reward signals based on task completion, efficiency, and hallucination checks across eight distinct shopping scenarios to ensure agents handle multi-turn workflows and tool use correctly without inventing product ids.
Hugging Face introduced Ecom-RLVE, an open-source reinforcement learning environment designed to train and evaluate conversational agents for e-commerce. The framework expands upon RLVE-Gym by moving from single-turn text puzzles to complex, multi-turn agentic workflows that require tool use, such as catalog searches and cart operations. It features an adaptive difficulty curriculum and provides verifiable rewards based on task success (F1 score on product/variant/qty tuples), efficiency, and hallucination penalties, ensuring agents do not invent product IDs they did not retrieve.