WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
Summary
WeVisForensics introduces a self-evolving multi-agent framework with dual-timescale policy optimization (DTPO) for detecting AI-generated videos, achieving 95.2% average detection accuracy—9.0% above the prior best detector—with localized forensic evidence, plus a curated ForenCue-30K dataset.
View Cached Full Text
Cached at: 11/20/26, 07:38 AM
Paper page - WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
Source: https://huggingface.co/papers/2611.21373
Abstract
WeVisForensics coordinates self-evolving visual and audio forensic inspector agents under a dual-timescale reinforcement learning policy to detect generated-video artifacts with localized evidence and high accuracy.
Recent advances invideo generationcall for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-passchain-of-thought reasoningthat overlooks brief or localized artifacts, or on predefinedmulti-agent workflowsthat 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, anagentic frameworkin which amain investigator agentcoordinates aself-evolving libraryofforensic inspector sub-agentsspanningvisual 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. Ourdual-timescale policy optimizationstrategy,DTPO, closes this loop through fastreinforcement learningof the investigator and slower refinement of the inspectors, guided byannotated artifact intervals, to report subtle artifacts they once dismissed. Furthermore, we curateForenCue-30K, combining role-specific forensic annotations and interaction trajectories to supervise individual inspections and their coordination, with an accompanyingreinforcement-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.
View arXiv pageView PDFProject pageGitHub25Add to collection
Get this paper in your agent:
hf papers read 2611\.21373
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper1
#### tencent/WeVisForensics Video-Text-to-Text• Updatedabout 1 hour ago • 10
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2611.21373 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2611.21373 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
This paper introduces FaceVid-Forensics-100K, a large-scale deepfake video dataset with fine-grained annotations, and proposes a multi-agent forensic reasoning framework (ARGUS) that uses four specialized expert agents and a judge agent to outperform closed-source models on deepfake detection.
Native Active Perception as Reasoning for Omni-Modal Understanding
Introduces OmniAgent, an omni-modal agent that uses an iterative Observation-Thought-Action cycle with active perception to achieve superior long video understanding, outperforming larger models like Qwen2.5-VL-72B on benchmarks.
OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains
OmniVideo-100K introduces an automated data engine with entity-anchored scripting and clue-guided QA generation to improve audio-visual reasoning and temporal consistency, achieving significant performance gains across multiple benchmarks.
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
O-VAD introduces a training-free agentic framework for industrial video anomaly detection that tracks object state evolution over time and reasons over temporal trajectories to identify abnormal objects, outperforming existing VLM and VAD methods on three datasets.
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
VideoSeeker introduces a paradigm for instance-level video understanding that integrates agentic reasoning with visual prompts, achieving superior performance through automated data synthesis and reinforcement learning, outperforming GPT-4o and Gemini-2.5-Pro.