Metraipolis › archive › dc_cd382e9530db

TGR: Advancing Industrial Recommendation from Generative-Paradigm Ranking toward Unified Generation and Reasoning — arXiv:2609.00986

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00986
License (as archived): CC0-1.0
Archived: 2026-10-17T07:10:05.595Z
SHA-256 of the archived text: f9e4b8782788c6ff0fe7b47be75fe3c24ee9cb917c334b279c1ec0282b809521
Stable URL of this page: https://metraipolis.com/documento/dc_cd382e9530db

How to cite

TGR: Advancing Industrial Recommendation from Generative-Paradigm Ranking toward Unified Generation and Reasoning — arXiv:2609.00986 — arXiv (en), https://arxiv.org/abs/2609.00986 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd382e9530db (Metraipolis archive dc_cd382e9530db, sha256 f9e4b8782788c6ff0fe7b47be75fe3c24ee9cb917c334b279c1ec0282b809521)

BibTeX

@misc{dccd382e9530db,
  title = {TGR: Advancing Industrial Recommendation from Generative-Paradigm Ranking toward Unified Generation and Reasoning — arXiv:2609.00986},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00986},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd382e9530db; sha256 f9e4b8782788c6ff0fe7b47be75fe3c24ee9cb917c334b279c1ec0282b809521},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00986. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial recommender systems typically rely on cascaded retrieval, pre-ranking, ranking, and reranking stages, whose separately optimized models limit scaling, fragment decision making, and lack semantic knowledge and reasoning. We present TGR (Tencent Generative Recommendation), an industrial framework that advances recommendation toward the generative paradigm along three coupled directions. TGR-GenRank upgrades ranking through CCFormer, which combines unified feature tokenization, a scalable Transformer backbone, feature-field separated cross attention, subspace token mixing, and hierarchical sequence compression while retaining per-item multi-task outputs. TGR-GenRec explores end-to-end generation under two paradigms: BARGE bridges item-boundary loss and semantic drift in hierarchical semantic-ID generation through item context-aware attention, hierarchical path reranking, and orthogonal dual-path decoding; HiGR performs whole-slate generation with prefix-structured semantic IDs, coarse-to-fine decoding, and listwise multi-objective alignment. TGR-Reason injects offline-generated semantic-ID reason tokens into online decoding, providing reasoning without request-time rollout. TGR is deployed across Tencent production surfaces serving hundreds of millions of users. CCFormer delivers significant gains in five A/B-tested scenarios and is fully launched in two, including +3.57% CTR and +1.71% advertising revenue. BARGE improves Hit@5 by 10.2-16.9% and yields +0.60% CTR and +1.70% reading time after full rollout. HiGR improves offline slate quality by 15.9-21.3% with a 5x inference speedup and achieves up to +1.22% watch time and +1.73% video views. TGR-Reason raises cold-start new-user Hit@1 by 477.8% and delivers +1.75% effective consumption and +13.09% new-user exposure-to-conversion online.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.00986 — 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 2026-10-17T07:00:39.710Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).