aiqbench analysis
Tencent's HiGR framework addresses critical bottlenecks in industrial-scale slate recommendation by decoupling high-level list planning from fine-grained decoding, achieving a 5x inference speedup while improving offline quality by over 10%. The system leverages a structured discrete space via PCRQ-VAE and coarse-grained preference embeddings to optimize global slate structure, resulting in measurable gains in watch time and video plays during online A/B tests. This approach demonstrates that architectural shifts toward hierarchical generation can effectively reconcile semantic planning efficiency with holistic ranking fidelity in real-world deployments.
HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent
arXiv:2512.24787v4 Announce Type: replace-cross Abstract: Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. While recent generative recommendation methods have shown strong potential in modeling item sequences with semantic IDs, directly applying them to industrial-scale slate recommendation faces a fundamental disconnect: entangled SID spaces confound high-level list planning, fine-grained autoregressive decoding over long sequences limits semantic planning efficiency, and token-level objectives misalign with holistic slate quality. In this paper, we propose HiGR, an industrial-scale hierarchical generative framework for slate recommendation that bridges this disconnect through a co-designed pipeline. First, HiGR learns structured SIDs via a Prefix-Contrastive Residual Quantized VAE (PCRQ-VAE). By enforcing high-level prefixes to capture shared semantics, PCRQ-VAE creates a controllable discrete space that acts as a prerequisite for efficient planning. Leveraging this structured space, our Hierarchical Slate Decoder (HSD) shifts autoregressive modeling from entangled token-level decoding to coarse-grained preference embeddings. This design significantly reduces inference latency while allowing explicit global slate structure planning. Finally, this stable planning space enables an ORPO-based listwise alignment mechanism to optimize triple-objective implicit feedback-ranking fidelity, genuine user interest, and diversity. Extensive offline experiments show that HiGR outperforms state-of-the-art baselines by over 10% in offline recommendation quality while achieving a $5\times$ inference speedup. Online A/B tests on Tencent platforms further improve watch time by 1.22% and video plays by 1.73%. HiGR has been deployed on multiple Tencent platform surfaces, serving hundreds of millions of users and proving its industrial-scale applicability.
Abstract:Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. While recent generative recommendation methods have shown strong potential in modeling item sequences with semantic IDs, directly applying them to industrial-scale slate recommendation faces a fundamental disconnect: entangled SID spaces confound high-level list planning, fine-grained autoregressive decoding over long sequences limits semantic planning efficiency, and token-level objectives misalign with holistic slate quality. In this paper, we propose HiGR, an industrial-scale hierarchical generative framework for slate recommendation that bridges this disconnect through a co-designed pipeline. First, HiGR learns structured SIDs via a Prefix-Contrastive Residual Quantized VAE (PCRQ-VAE). By enforcing high-level prefixes to capture shared semantics, PCRQ-VAE creates a controllable discrete space that acts as a prerequisite for efficient planning. Leveraging this structured space, our Hierarchical Slate Decoder (HSD) shifts autoregressive modeling from entangled token-level decoding to coarse-grained preference embeddings. This design significantly reduces inference latency while allowing explicit global slate structure planning. Finally, this stable planning space enables an ORPO-based listwise alignment mechanism to optimize triple-objective implicit feedback-ranking fidelity, genuine user interest, and diversity. Extensive offline experiments show that HiGR outperforms state-of-the-art baselines by over 10% in offline recommendation quality while achieving a $5\times$ inference speedup. Online A/B tests on Tencent platforms further improve watch time by 1.22% and video plays by 1.73%. HiGR has been deployed on multiple Tencent platform surfaces, serving hundreds of millions of users and proving its industrial-scale applicability.
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
arXiv:2512.24787 [cs.IR]
(or arXiv:2512.24787v4 [cs.IR] for this version)
Full text under the publisher's open licence · 256 words
Related coverage
HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent
arXiv · Jun 12, 2026
HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent
arXiv · Jun 10, 2026
How Generative Recommenders Are Redefining RecSys at Scale
NVIDIA · Aug 20, 2026
A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing
arXiv · Aug 6, 2026