Metraipolis › archive › dc_ecccb5731df3

TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework — arXiv:2611.09091

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09091
License (as archived)
CC0-1.0
Archived
2026-11-09T22:41:26.282Z
SHA-256 of the archived text
4dde4db3c7af2dcd537e7e2aba94cc70dfada5f9349501ee1cadc571e0db6a60
Stable URL of this page
https://metraipolis.com/documento/dc_ecccb5731df3

How to cite

TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework — arXiv:2611.09091 — arXiv (en), https://arxiv.org/abs/2611.09091 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecccb5731df3 (Metraipolis archive dc_ecccb5731df3, sha256 4dde4db3c7af2dcd537e7e2aba94cc70dfada5f9349501ee1cadc571e0db6a60)
BibTeX
@misc{dcecccb5731df3,
  title = {TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework — arXiv:2611.09091},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09091},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecccb5731df3; sha256 4dde4db3c7af2dcd537e7e2aba94cc70dfada5f9349501ee1cadc571e0db6a60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09091. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative modeling, particularly Decision Transformers, shows promise in auto-bidding strategies. However, it struggles with limited exploration in static offline datasets, vulnerability to dynamic environmental shifts, and a reliance on heuristic return-to-go (RTG) specifications that may yield suboptimal performance on unseen traffic. To address these challenges, we propose the Two-stage Uncertainty-aware Generative Auto-Bidding (TUGB) framework. TUGB integrates generative sequence modeling with Reinforcement Learning (RL). It employs a two-stage pipeline where a pre-trained Generative Bidding Model is fine-tuned via an ensemble-based Uncertainty-aware Environment Model. This approach quantifies epistemic uncertainty to penalize high-risk trajectories and evolves the policy from RTG-conditioning to direct bidding optimization. Extensive experiments demonstrate that TUGB significantly outperforms SOTA baselines. Notably, full-scale deployment on JD Search Ad achieved a 2.32\% increase in cost and 3.57\% in target cost, validating its industrial efficacy, while its successful adaptation to subsequent mechanism upgrades and JD Food Delivery Ad further validates TUGB's superior generalization capability.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.09091 — 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 2026-11-09T22:33:47.152Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).