AgenticGen: Reward-Guided Agentic Video Generation for Advertising
AgenticGen applies DPO and GRPO reward-guided reasoning to ad video generation, improving TikTok CTR 2.72%, CVR 2.63%, and Advv 9.61%.
AgenticGen decomposes advertising video generation into two trainable reasoning stages, strategy selection and draft generation, supervised by online business feedback. It learns a performance-based reward from accumulated online feedback plus a rubric-based reward aligned with human quality standards, then optimizes policies with DPO followed by GRPO using process and outcome rewards. Online A/B experiments in the TikTok advertising system show CTR up 2.72%, CVR up 2.63%, and Advv up 9.61% over an SFT baseline.
- Decomposes ad generation into trainable strategy-selection and draft-generation stages supervised by business feedback.
- Learns performance-based reward from online feedback plus rubric-based reward aligned with human quality standards.
- DPO shifts policies toward online preferences; GRPO refines with process and outcome rewards.
- Online A/B tests show CTR +2.72%, CVR +2.63%, Advv +9.61% over SFT baseline.
Full article183 words · extracted from huggingface.co · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.09187