arXiv cs.AI· Bohao Li, Dinglun Cao, Pengcheng Huang, Yingda Tang, Zhiting Zhao, Yi Cao, Jilei Fu, Miao Yan, Tianying Liu, Heng Chang, Bowen Du·· 12 小时前AI 评分24
EASformer：面向工业生成式排序的环境-动作-状态对齐架构
EASformer: Environment-Action-State Alignment for Industrial Generative Ranking
AI 导读
EASformer 提出环境-动作-状态解耦架构，为工业应用排序构建历史与非序列 token 共享的对齐上下文环境空间，并将用户动作与候选侧上下文分离。在真实工业应用市场的离线基准上，其 AUC 达 0.89411，较已部署基线相对提升 0.88%；在线 A/B 测试中两个真实排序场景的 eCPM 分别相对提升 1.26% 和 3.94%。
正文 · 原文
Authors:Bohao Li, Dinglun Cao, Pengcheng Huang, Yingda Tang, Zhiting Zhao, Yi Cao, Jilei Fu, Miao Yan, Tianying Liu, Heng Chang, Bowen Du
Abstract: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.
| Comments: | 10 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27691 [cs.AI] |
| (or arXiv:2610.27691v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27691 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bohao Li [view email]
[v1]
Tue, 20 Oct 2026 06:08:07 UTC (468 KB)
来源：arXiv cs.AI · arxiv.org