Paper Detail
Xingyuan Bu, Chengru Song, Hao Zhou, Tao Zhou, Dong Li, Wei Li, Shilong Li, Hao Shi, Yongxin Guo, Donghao Zhou, Qiangpeng Yang, Shilei Wen
Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realistic clips from multimodal conditions, yet they do not optimize how a product should be transformed into an effective advertisement or how future generation should be improved from online business feedback. To close this loop, we propose AgenticGen, a reward-guided agentic framework that decomposes advertising video generation into two trainable reasoning stages, strategy selection and draft generation, thereby exposing optimization targets that online business feedback can supervise. AgenticGen learns a performance-based reward from accumulated online feedback and a complementary rubric-based reward aligned with human quality standards, then uses them to supervise policy optimization. DPO first moves the agentic policies toward online preferences, and GRPO further refines both stages with process and outcome rewards. Offline experiments validate the reward models and successive policy optimization. Online A/B experiments in the TikTok advertising system show that AgenticGen after DPO and GRPO improves CTR by 2.72%, CVR by 2.63%, and Advv by 9.61% over the SFT baseline.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{bu2026agenticgen,
title = {AgenticGen: Reward-Guided Agentic Video Generation for Advertising},
author = {Xingyuan Bu and Chengru Song and Hao Zhou and Tao Zhou and Dong Li and Wei Li and Shilong Li and Hao Shi and Yongxin Guo and Donghao Zhou and Qiangpeng Yang and Shilei Wen},
year = {2026},
abstract = {Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realistic clips from multimodal conditions, yet they do not optimize how a product should be transformed into an effective advertisement or how future generation should be improved from online business feedback. To close this loop, we propose AgenticGen, a reward-guided agentic framework},
url = {https://huggingface.co/papers/2609.09187},
keywords = {DPO, GRPO, reward-guided agentic framework, policy optimization, process and outcome rewards, CTR, CVR, huggingface daily},
eprint = {2609.09187},
archiveprefix = {arXiv},
}
{}