E-commerce video reasoning boosted by active evidence seeking model

Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning

Computer Vision and Pattern RecognitionArtificial Intelligence

Summary

People often compare products by watching many e-commerce videos, but current AI models mostly understand videos one by one and struggle to compare details across multiple videos. The authors created AdsCVR, a new test set with thousands of videos and questions to challenge AI to reason across videos using images, speech, and text. They also developed AdSeek, a smart system that actively picks when and where to look and listen in videos to gather the right clues, improving reasoning accuracy. This approach notably outperforms prior models and works well on other video reasoning tasks too.

What this means in practice

  • For e-commerce platform developers: Improve product comparison tools by enabling AI to reason across multiple promotional videos for better consumer insights.$Commercial implications: This enables e-commerce companies to offer smarter, AI-powered video comparison features, enhancing shopping experience and sales.
  • For multimedia content analysts: Create systems that actively select important audio-visual evidence in large video datasets to enhance cross-video analysis accuracy.

Authors

Jinghan Zhao, Yiman Hu, Liang Wu, Jian Xu, Bo Zheng

Abstract

E-commerce videos are information-dense and frequently compared by consumers evaluating products and merchants assessing marketing strategies. However, existing multimodal models mainly focus on single-video understanding and have limited ability to compare information across videos. We introduce AdsCVR, the first e-commerce cross-video reasoning benchmark, containing 2,483 videos and 6,110 question-answer pairs across six reasoning dimensions. Cross- video reasoning requires models to locate fine-grained evidence among many redundant frames and integrate visual details, speech, and on-screen text. We therefore propose AdSeek, an agentic framework that dynamically selects visual and audio tools during multi-turn exploration, replacing static uniform sampling with active evidence acquisition. To address the sparse credit assignment of reinforcement learning, we develop an offline trajectory rectification mechanism that identifies reasoning errors and missing multimodal evidence in RL-generated trajectories. The corrected trajectories provide supervised fine-tuning signals that reduce biases learned during RL. This mechanism supports a rectified bootstrapping pipeline in which initial RL exposes reasoning bottlenecks, supervised fine-tuning corrects them, and a final RL stage further improves the policy. AdSeek achieves 74.30 percent accuracy on the AdsCVR test split, outperforming its Qwen3-VL-8B-Instruct backbone by 27.90 percentage points. It also generalizes to the open- domain CrossVid benchmark, demonstrating effective active evidence gathering.