Tag
The author built a test store with 7 common dark patterns and ran 4 AI shopping agents (ChatGPT, Claude Opus/Sonnet/Haiku 5.5 via Buddy) through it; the top models scored A+ by avoiding deceptive pricing, pre-ticked add-ons, and urgency tricks, with a harder round 2 planned.
TikTok announced a conversational shopping agent that leverages user data for personalized product picks with in-app checkout, following Meta's Muse which has 5 million+ downloads. The piece questions whether these agents function as opt-in tools or platforms silently steering consumer choices, especially given the companies' ad-driven business models.
This paper introduces LOFA, a framework that enables LLM-based shopping agents to learn from real online user interaction logs using reinforcement learning over purchase outcomes and feedback-aware on-policy distillation, improving recommendation quality and user satisfaction.
MMShopBench introduces a real-log benchmark for multimodal, multi-turn shopping agents, requiring joint inference from user images and dialogue, with an offline sandbox and training set to improve open-source model performance.
Introduces EComAgentBench, a benchmark for evaluating LLM-based shopping agents on long-horizon tasks with hidden intents distributed across queries, profiles, and clarifications. The benchmark uses real Amazon products and automated scoring, revealing that even the best model achieves only 57.1% accuracy.