# The Layout Is the Model: On Action-Item Coupling in Generative Recommendation

arXiv: https://arxiv.org/abs/2510.16804 · HTML: https://mlsanity.com/paper/2510.16804/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2025.

## Built on by (most cited first, 1 of 1)

- [Beyond Interleaving: Causal Attention Reformulations for Generative Recommender Systems](https://mlsanity.com/paper/2603.10369/) (2026)

## Abstract (arXiv)

Generative Recommendation (GR) models treat a user's interaction history as a sequence to be autoregressively predicted. When both items and actions (e.g., watch time, purchase, comment) are modeled, the layout-the ordering and visibility of item/action tokens-critically determines what information the model can use and how it generalizes. We present a unified study of token layouts for GR grounded in first principles: (P1) maximize item/action signal in both input/output space, (P2) preserve the conditioning relationship "action given item" and (P3) no information leakage. While interleaved layout (where item and action occupy separate tokens) naturally satisfies these principles, it also bloats sequence length with larger training/inference cost. On the non-interleaved front, we design a novel and effective approach, Lagged Action Conditioning (LAC), which appears strange on the surface but aligns well with the design principles to yield strong accuracy. Comprehensive experiments on public datasets and large-scale production logs evaluate different layout options and empirically verifies the design principles. Our proposed non-interleaved method, LAC, achieves competitive or superior quality at substantially lower FLOPs than interleaving. Our findings offer actionable guidance for assembling GR systems that are both accurate and efficient.