# FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning

arXiv: https://arxiv.org/abs/2602.22963 · HTML: https://mlsanity.com/paper/2602.22963/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images](https://mlsanity.com/paper/2403.11703/) (2024)
- [LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents](https://mlsanity.com/paper/2311.05437/) (2023)
- [LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token](https://mlsanity.com/paper/2501.03895/) (2025)
- [Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues](https://mlsanity.com/paper/2003.06711/) (2020)
- [BERT: A Review of Applications in Natural Language Processing and Understanding](https://mlsanity.com/paper/2103.11943/) (2021)
- [Improving Fake News Detection by Using an Entity-enhanced Framework to Fuse Diverse Multimodal Clues](https://mlsanity.com/paper/2108.10509/) (2021)
- [FakeSV: A Multimodal Benchmark with Rich Social Context for Fake News Detection on Short Video Platforms](https://mlsanity.com/paper/2211.10973/) (2022)
- [Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools](https://mlsanity.com/paper/2510.08480/) (2025)
- [FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process](https://mlsanity.com/paper/2407.16670/) (2024)
- [Cross-modal Contrastive Learning for Multimodal Fake News Detection](https://mlsanity.com/paper/2302.14057/) (2023)
- [Towards Automatic Detection of Misinformation in Online Medical Videos](https://mlsanity.com/paper/1909.01543/) (2019)
- [Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors](https://mlsanity.com/paper/2306.05241/) (2023)
- [Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning](https://mlsanity.com/paper/2505.16836/) (2025)
- [Multi-Modal Semantic Inconsistency Detection in Social Media News Posts](https://mlsanity.com/paper/2105.12855/) (2021)
- [Consistency-aware Fake Videos Detection on Short Video Platforms](https://mlsanity.com/paper/2504.21495/) (2025)
- [Unsupervised Explanation Generation via Correct Instantiations](https://mlsanity.com/paper/2211.11160/) (2022)
- [T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search](https://mlsanity.com/paper/2505.19768/) (2025)
- [FMNV: A Dataset of Media-Published News Videos for Fake News Detection](https://mlsanity.com/paper/2504.07687/) (2025)
- [Mining the Social Fabric: Unveiling Communities for Fake News Detection in Short Videos](https://mlsanity.com/paper/2508.07992/) (2025)

## Built on by (most cited first, 5 of 5)

- [IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools](https://mlsanity.com/paper/2605.20682/) (2026)
- [IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval](https://mlsanity.com/paper/2606.08144/) (2026)
- [TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos](https://mlsanity.com/paper/2608.30704/) (2026)
- [VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction](https://mlsanity.com/paper/2610.06293/) (2026)
- [X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning](https://mlsanity.com/paper/2610.16811/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have substantially advanced video misinformation detection through unified multimodal reasoning, but they often rely on fixed-depth inference and place excessive trust in internally generated assumptions, particularly in scenarios where critical evidence is sparse, fragmented, or requires external verification. To address these limitations, we propose FactGuard, an agentic framework for video misinformation detection that formulates verification as an iterative reasoning process built upon MLLMs. FactGuard explicitly assesses task ambiguity and selectively invokes external tools to acquire critical evidence, enabling progressive refinement of reasoning trajectories. To further strengthen this capability, we introduce a two-stage training strategy that combines domain-specific agentic supervised fine-tuning with decision-aware reinforcement learning to optimize tool usage and calibrate risk-sensitive decision making. Extensive experiments on FakeSV, FakeTT, and FakeVV demonstrate FactGuard's state-of-the-art performance and validate its excellent robustness and generalization capacity.