GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search
This paper introduces GLOBE, an agentic framework for continual self-improvement in product listing optimization.
This paper introduces a novel agentic framework for continual self-improvement in product listing optimization, which is distinct from existing approaches that treat structured listings as free-form text.
Before reading this…
Applications
- →Product listing optimization
- →Generative search
To understand this paper, make sure you know these concepts first:
- Understanding of product listing optimization and generative searchfind papers →
- Basic knowledge of machine learning and natural language processingfind papers →
Abstract
More Like ThisOptimizing product listings for generative search requires language agents not only to rewrite effectively but also to continually self-improve by retaining successful strategies across diverse categories. However, existing approaches often treat structured listings as free-form text, leaving effective strategies implicit in prompts, search trajectories, or rewritten outputs rather than accumulating them as a reusable agentic memory. To address this limitation, we introduce GLOBE, an agentic framework that drives continual self-improvement by storing optimization knowledge in an evolving handbook of explicit, field-scoped behaviors. In each episode, an Editor applies relevant behaviors and receives rank-based feedback, which a Reflector converts into behavior updates. Crucially for dependable execution in real-world settings, a Moderator removes redundant proposals, a Curator commits accepted changes, and consistently harmful behaviors are deactivated. This cycle transforms episodic feedback into a persistent, field-scoped optimization memory. Experiments show that structured behaviors outperform monolithic prompt optimization, while feedback-driven evolution and moderation further improve effectiveness and reduce downside risk. The learned behaviors also remain effective on unseen product categories, suggesting that agentic memory evolution supports interpretable and transferable product optimization.