Home / AI Research / WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
WEAI Research
WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
by tencent · Yipeng Du, Yuxi Li, Ying Zhang, Chong Sun, Chen Li, Jing Lyu
Recent advances in video generation call for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-pass chain-of-thought reasoning that overlooks brief or localized artifacts, or on predefined multi-agent workflows that offer limited flexibility in selecting relevant inspections. Even with adaptive investigation, optimizing the investigation policy alone does not directly improve the forensic capabilities of fixed experts. We introduce WeVisForensics, an agentic framework in which a main investigator agent coordinates a self-evolving library of forensic inspector sub-agents spanning visual and audio cues. The investigator learns…
Upvotes53
Comments3
Published15 Nov 2026