cs.AINov 2, 2026

Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation

Authors: Yuxuan Hu, Yingyi Zhang, Wenlin Zhang, Chao Zhang, Haotian Nan, Ziwei Liu, Jiancheng Dong, Tongzhou Wu, 

Organizations: City University of Hong Kong Hong Kong, China · Platform and Content Group Tencent Shenzhen, China

Abstract

Semantic-ID-based (SID) generative recommendation (GR) represents each item as a sequence of discrete tokens and predicts the next item through autoregressive SID generation. However, existing methods face two challenges. First, insufficient shared context modeling for user sequences: full-history and recent behaviors provide overlapping yet complementary evidence, but modeling them within a single sequence may dilute current cues, whereas processing them through separate streams may fail to coordinate them. Second, insufficient personalized adaptation in progressive SID decisions: although decoder states evolve with generated prefixes, existing models typically use a shared output-side transformation across recommendation instances, without explicitly selecting a transformation suited to the current user need. To address these challenges, we propose Multi-View Thinking with Adaptive Generation (MV-Thinker), a framework that Thinks Globally and Generates Personally. First, Multi-View Temporal Thinking uses view-specific thinking queries and readers over overlapping full-history and recent-history views, coordinating both sources into complementary user-conditioned contexts before SID generation. Second, Hierarchical Residual Adaptation organizes lightweight adapters into nested residual paths before a shared vocabulary projection, adaptively transforming context-bearing decoder states for SID decisions. Extensive experiments on four public datasets demonstrate that MV-Thinker consistently outperforms strong discriminative and generative recommendation baselines across multiple ranking metrics. The implementation code and datasets are available on: https://anonymous.4open.science/r/MV-Thinker

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Learning Better Reasoning for Generative Recommendation with Semantic IDs

    Sep 24, 2026Mengdan Zhu, Yufan Zhao, Sophie Di +5Semantic ID RecommendationSequential Recommendation

  2. Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation

    Jul 27, 2026Junting Wang, Xinrui He, Yunzhe Li +1Semantic ID RecommendationLanguage Model Decoding

  3. REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation

    Oct 27, 2026Yuxi Huang, Silin Zhou, Chenhao Wang +6Generative RecommendationSemantic ID Recommendation