UniPolicy is a unified objective‑specific policy framework for search advertising that jointly optimizes relevance, click propensity, and commercial value. It uses objective‑aware prefix tokens, sparse MoE‑LoRA routing, and residual FFNs to decouple parameters within a shared backbone, and constructs pairwise preferences from multi‑stage behavioral feedback to strengthen clicked candidates. In large‑scale offline tests and a 7‑day online A/B test, UniPolicy improves CTR by 0.71%, RPS by 1.58%, and advertising revenue by 1.32% while keeping serving latency stable.
By Kun Yao, Yuhang Zhou, Yichi Zhang, Zeliang Tong, Shengri Xue, Haitao Wang, Siyu Lu, Qianlong Xie, Xingxing Wang
arXiv:2609.08211v1 Announce Type: new
Abstract: Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing...
By Shanwen Mao, Hao Zhang, Guangtao nie, Zhiheng Li, Huimu Wang, Sulong Xu, Gu Simiu
arXiv:2607. 17281v1 Announce Type: cross Abstract: Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals.
By Yuejia Dou, Hesong Wang, Xinyu Zhang, Tianyu Wang, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, Qi Qi
The paper introduces the Latent Advertiser Mixture Auction (LAMA), a token‑level advertising framework that integrates advertiser influence directly into the text generation process. Advertisers provide local continuation values that shape next‑token policies, and the platform decodes these through a latent mixture while updating an allocation posterior. LAMA is shown to satisfy Markov DSIC and IR, achieve near‑optimal KL‑regularized welfare, and, in proof‑of‑concept experiments on commercial‑search queries, improve platform welfare and revenue without compromising user‑facing response quality.
By Hanbing Liu, Bowei Zhang, Changyuan Yu, Yinyu Ye, Qi Qi
arXiv:2608. 13833v1 Announce Type: cross Abstract: Conversational advertising aims to deliver useful ads within multi-turn assistant interactions.
By Simiao Zuo, Chenhui Xu, Yimeng Jia, Qiang Lou, Jian Jiao, Denis Charles
arXiv:2604. 05845v2 Announce Type: replace-cross Abstract: Auto-bidding services optimize real-time bidding strategies for advertisers under key performance indicator (KPI) constraints such as target return on investment and budget.
By Linghui Meng, Chun Gan, Shengsheng Niu, Chengcheng Zhang, Chenchen Li, Chuan Yang, Yi Mao, Xin Zhu, Jie He, Zhangang Lin, Ching Law
arXiv:2510. 01167v2 Announce Type: replace-cross Abstract: Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective.
By Yiran Shen, Yu Xia, Jonathan Chang, Prithviraj Ammanabrolu
arXiv:2607. 03886v1 Announce Type: cross Abstract: Sponsored search plays a crucial role as a revenue stream for search engines, wherein advertisers competitively bid on keywords that align with the users' search queries.
By Md Omar Faruk Rokon, Andrei Simion, Weizhi Du, Musen Wen, Hong Yao, Kuang-chih Lee
arXiv:2601. 02754v3 Announce Type: replace-cross Abstract: With the rapid development of e-commerce, auto-bidding has become a key asset in optimizing advertising performance under diverse advertiser environments.
By Mingming Zhang, Na Li, Zhuang Feiqing, Hongyang Zheng, Jiangbing Zhou, Wang Wuyin, Sheng-jie Sun, XiaoWei Chen, Junxiong Zhu, Lixin Zou, Chenliang Li
arXiv:2608. 06792v1 Announce Type: cross Abstract: Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior.
By Oseong Choi, Hoeinn Kim, Jihoon Lee, Byungsoo Kang, Taeyeong Jang
arXiv:2602. 08261v2 Announce Type: replace Abstract: Auto-bidding systems strive to maximize marketing value while maintaining high compliance with efficiency constraints, such as Target Cost-Per-Action (CPA).
By Binglin Wu, Yingyi Zhang, Xianneng Li, Ruyue Deng, Chuan Yue, Weiru Zhang, Xiaoyi Zeng
Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization.