GLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search

2026-02-05

AI Summary

Existing generative recommender systems struggle to effectively model users’ long historical behavior sequences, which limits recommendation accuracy. To address this challenge, this work proposes the SID-Tier framework, which encodes long-term user interactions into a unified interest vector through semantic-driven codebook compression and dynamically retrieves relevant historical behaviors via a semantic hard-search mechanism. The approach further incorporates semantic neighbor augmentation and adaptive codebook scaling to mitigate data sparsity in large-scale item spaces. Extensive experiments on two real-world large-scale datasets, TAOBAO-MM and KuaiRec, demonstrate that the proposed method significantly outperforms state-of-the-art baselines, substantially advancing the performance of generative recommendation systems.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a transformative paradigm, they face hurdles in effectively modeling extensive historical sequences. To address this challenge, we propose GLASS, a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search. We first introduce SID-Tier, a module that maps long-term interactions into a unified interest vector to enhance the prediction of the initial SID token. Unlike traditional retrieval models that struggle with massive item spaces, SID-Tier leverages the compact nature of the semantic codebook to incorporate cross features between the user's long-term history and candidate semantic codes. Furthermore, we present semantic hard search, which utilizes generated coarse-grained semantic ID as dynamic keys to extract relevant historical behaviors, which are then fused via an adaptive gated fusion module to recalibrate the trajectory of subsequent fine-grained tokens. To address the inherent data sparsity in semantic hard search, we propose two strategies: semantic neighbor augmentation and codebook resizing. Extensive experiments on two large-scale real-world datasets, TAOBAO-MM and KuaiRec, demonstrate that GLASS outperforms state-of-the-art baselines, achieving significant gains in recommendation quality. Our codes are made publicly available to facilitate further research in generative recommendation.

Problem

• generative recommender
• long-sequence modeling
• user behavioral patterns
• semantic search
• recommendation accuracy

Innovation

• Generative Recommender
• Long-sequence Modeling
• SID-Tier
• Semantic Search
• Semantic Codebook