cs.CVNov 16, 2026

WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection

Authors: Yipeng Du, Yuxi Li, Ying Zhang, Chong Sun, Chen Li, Jing Lyu, Ying Tai

Organizations: Nanjing University · WeChat Vision, Tencent Inc.

Abstract

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 which artifact type to examine, over which window, and when to conclude, and these interactions provide shared feedback for both levels of agents. Our dual-timescale policy optimization strategy, DTPO, closes this loop through fast reinforcement learning of the investigator and slower refinement of the inspectors, guided by annotated artifact intervals, to report subtle artifacts they once dismissed. Furthermore, we curate ForenCue-30K, combining role-specific forensic annotations and interaction trajectories to supervise individual inspections and their coordination, with an accompanying reinforcement-learning pool. Experiments show that WeVisForensics averages 95.2% detection accuracy across in-domain, out-of-domain and agentic benchmarks, 9.0% above the strongest prior detector, while grounding its verdicts in localized evidence.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection

    Apr 18, 2026Hongyuan Qi, Feifei Shao, Ming Li +2Multi-Agent DebateDeepfake Detection

  2. Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

    Oct 22, 2026Zhuoran Zhang, Yang Shi, Qixun Wang +11Synthetic Video Detection BenchmarksExplainable Deepfake Detection

  3. FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detection

    Sep 5, 2026Jiaoyang Chen, Bin Hu, Jingyu Hu +3AI-Generated Image DetectionImage Forgery Detection