Abstract
Product catalogs are the backbone of e-commerce sites, yet a large number of structured attributes (SAs) such as material, color, and shape often have missing values. Typically, SA values are extracted from product information, including titles and descriptions. While LLM-based generator-evaluator frameworks have demonstrated effectiveness for SA prediction, they face challenges when the Generator and Evaluator produce conflicting outputs, as either component can make mistakes.
We introduce CatalogAgent, a novel agentic system that continuously improves Generator and Evaluator models for e-commerce catalog enrichment. When disagreements arise from (1) internal conflicts between the LLM-based Generator and Evaluator, or (2) external feedback from sellers on LLM outputs, a Supervisor Agent intervenes to mediate these conflicts and make final decisions. The system also incorporates a Memory Base and a Memory Summarizer that stores Supervisor Agent activities from individual cases and aggregates patterns into learnings. These learnings are fed back to the worker Generator and Evaluator LLMs, enabling self-improvement without human intervention.
Through context engineering, the system successfully transfers the Supervisor's capabilities to the Generator and Evaluator, improving their performance by 15.24% and 13.98%, respectively. Our experiments demonstrate a new paradigm of Supervisor Agent-mediated self-learning systems for improving generative AI model accuracy.
Blogger's Review: CatalogAgent showcases how intervention by a Supervisor Agent can resolve conflicts in generative models, enabling self-learning and significantly improving model accuracy. This approach offers an innovative solution for product catalog management in e-commerce, warranting further exploration of its application potential in other domains.