Metraipolis › archive › dc_5bf84fd2fb89

EASformer: Environment-Action-State Alignment for Industrial Generative Ranking — arXiv:2610.27691

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.27691
License (as archived): CC0-1.0
Archived: 2026-10-21T07:06:46.875Z
SHA-256 of the archived text: 7ef3be0930059cecf25361dee5fc8970fb239dd642b638fc9a1d856669a9436f
Stable URL of this page: https://metraipolis.com/documento/dc_5bf84fd2fb89

How to cite

EASformer: Environment-Action-State Alignment for Industrial Generative Ranking — arXiv:2610.27691 — arXiv (en), https://arxiv.org/abs/2610.27691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bf84fd2fb89 (Metraipolis archive dc_5bf84fd2fb89, sha256 7ef3be0930059cecf25361dee5fc8970fb239dd642b638fc9a1d856669a9436f)

BibTeX

@misc{dc5bf84fd2fb89,
  title = {EASformer: Environment-Action-State Alignment for Industrial Generative Ranking — arXiv:2610.27691},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27691},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bf84fd2fb89; sha256 7ef3be0930059cecf25361dee5fc8970fb239dd642b638fc9a1d856669a9436f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern industrial ranking systems increasingly adopt generative recommendation (GR) paradigms, in which user behavior sequences and non-sequential (NS) features are tokenized and jointly modeled by Transformer-style backbones. This unified formulation provides a scalable interface for modeling long histories and heterogeneous features. However, sequence and NS representations often carry asymmetric semantics: historical representations may combine environment context with observed-action semantics, whereas candidate-side NS representations contain no observed action but incorporate richer supplementary context, such as user-item interaction features and recent behavior lists. Direct interaction between such representations can make query-key dot products compare different semantic objects, limiting meaningful cross-token interaction. To fill this gap, we propose EASformer, an Environment-Action-State disentangled architecture for industrial app ranking. EASformer constructs an explicitly aligned context environment space shared by historical and non-sequence tokens, while disentangling user actions from historical token and candidate-specific context form non-sequence tokens. Based on this aligned space, EASformer enables complementary historical action retrieval and state-conditioned action prediction. Furthermore, the disentangled design supports a Cloze-style self-supervised objective by masking historical actions and reusing the candidate prediction pathway. On an offline benchmark from a real-world industrial app marketplace, EASformer achieves an AUC of 0.89411, yielding a 0.88% relative improvement over the deployed baseline. Online A/B tests further support this advantage, with relative eCPM lifts of 1.26% and 3.94% across two real-world ranking scenarios.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.27691 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-21T07:05:43.435Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).