A Cascaded Generative Approach for e-Commerce Recommendations

ArXi:2605.11118v1 Announce Type: new Personalized fronts in large e-commerce marketplaces are often assembled from many independent components: static themes per page section ("placement"), retrieval systems to fetch eligible products per placement, and pointwise rankers to order content. While effective in optimizing for aggregate preferences, this paradigm is rigid and can limit personalization and semantic cohesion across the page. This makes it poorly suited to dynamic objectives and andising requirements over time. To address this, we.