TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on detecting videos made by AI, which can be tricky because the fake details are very subtle. They created a system called TUE-Detector that uses a special AI model trained to use different tools to find clues showing a video is fake. This system gathers evidence and reasons about it to decide if a video is AI-generated. Their experiments show that this approach works well for spotting fake videos.
AI-generated videosvideo forensicsmultimodal large language model (MLLM)tool-using AIartifact detectionevidence reasoningdeep learningvideo authenticitycomputer vision
Authors
Yichen Wu, Haoxuan Qu, Yongxing Dai, Yan Bai, Yihang Lou, Yuqi Lin, Hossein Rahmani, Jun Liu
Abstract
AI-generated video detection, which aims to distinguish AI-generated videos from real ones, has recently received increasing research attention. To perform this task reliably, a key challenge lies in accurately identifying subtle-yet-measurable unnatural artifacts. In this work, we address this challenge from a novel perspective of tool-mediated evidence discovery and propose Tool-Using Expert MLLM-based AI-generated Video Detector (TUE-Detector), a novel framework for AI-generated video detection. TUE-Detector trains a general MLLM into a task-tailored tool-using expert detector that learns to invoke suitable tools, collect concrete evidence of unnaturalness, and reason over the evidence for reliable detection. Meanwhile, TUE-Detector further introduces novel designs to equip the expert detector with high-quality and suitable tools. Extensive experiments demonstrate the effectiveness of our framework.