# OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensics

arXiv: https://arxiv.org/abs/2605.16962 · HTML: https://mlsanity.com/paper/2605.16962/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 16 May 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 32)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis](https://mlsanity.com/paper/2103.05630/) (2021)
- [NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media](https://mlsanity.com/paper/2104.05893/) (2021)
- [Detecting and Grounding Multi-Modal Media Manipulation](https://mlsanity.com/paper/2304.02556/) (2023)
- [Soft Adaptive Policy Optimization](https://mlsanity.com/paper/2511.20347/) (2025)
- [Generative Image Dynamics](https://mlsanity.com/paper/2309.07906/) (2023)
- [DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark](https://mlsanity.com/paper/2405.19707/) (2024)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs](https://mlsanity.com/paper/2406.08772/) (2024)
- [LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models](https://mlsanity.com/paper/2410.09732/) (2024)
- [LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report](https://mlsanity.com/paper/2405.00732/) (2024)
- [AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics](https://mlsanity.com/paper/2304.06870/) (2023)
- [D3: Scaling Up Deepfake Detection by Learning from Discrepancy](https://mlsanity.com/paper/2404.04584/) (2024)
- [Masked Face Recognition Challenge: The InsightFace Track Report](https://mlsanity.com/paper/2108.08191/) (2021)
- [FakeSV: A Multimodal Benchmark with Rich Social Context for Fake News Detection on Short Video Platforms](https://mlsanity.com/paper/2211.10973/) (2022)
- [On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection](https://mlsanity.com/paper/2410.23623/) (2024)
- [FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs](https://mlsanity.com/paper/2403.01988/) (2024)
- [FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process](https://mlsanity.com/paper/2407.16670/) (2024)
- [OpenSDI: Spotting Diffusion-Generated Images in the Open World](https://mlsanity.com/paper/2503.19653/) (2025)
- [MCFEND: A Multi-source Benchmark Dataset for Chinese Fake News Detection](https://mlsanity.com/paper/2403.09092/) (2024)
- [The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts](https://mlsanity.com/paper/2505.17476/) (2025)
- [FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter](https://mlsanity.com/paper/2508.19639/) (2025)
- [Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations](https://mlsanity.com/paper/2509.12653/) (2025)

## Abstract (arXiv)

Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite parametric knowledge, static training corpora, and limited perceptual resolution, creating a practical ceiling in dynamic open-world forensics -- particularly for real-time event verification requiring external clues and forgery segmentation demanding fine-grained scrutiny of local manipulations. To address these limitations, we shift from scaling up the self-contained model toward reaching beyond it. We propose OmniVL-Guard Pro, a tool-augmented agent that extends unified forensics from closed-world prediction to open-world clues-driven reasoning. OmniVL-Guard Pro integrates a tool environment spanning real-time event search, local cropping and zooming, edge-anomaly screening, face detection, video frame extraction, and SAM3-based segmentation. To generate high-quality tool-reasoning trajectories, we introduce Tree-Structured Self-Evolving Tool Trajectory Generation, which produces diverse trajectories through seed guidance, guider-free self-evolution, and weakly-hinted hard sample synthesis, yielding the Full-Spectrum Tool Reasoning (FSTR) dataset for training. We further propose Checker-Guided Agentic Reinforcement Learning (CGARL), which provides process-level supervision to penalize cases where the answer is correct but the reasoning is distorted. Extensive experiments demonstrate that OmniVL-Guard Pro achieves state-of-the-art performance across various tasks, and exhibits strong zero-shot generalization. The FSTR dataset and code for OmniVL-Guard Pro will be publicly released at https://github.com/shen8424/OmniVL-Guard-Pro.