Saved in:
Bibliographic Details
Main Authors: Li, Zehao, Yu, Hongwei, Jiang, Hao, Sheng, Qiang, Xu, Yilong, Bi, Baolong, Li, Yang, Yuan, Zhenlong, Cai, Yujun, Wang, Zhaoqi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.22963
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914353539710976
author Li, Zehao
Yu, Hongwei
Jiang, Hao
Sheng, Qiang
Xu, Yilong
Bi, Baolong
Li, Yang
Yuan, Zhenlong
Cai, Yujun
Wang, Zhaoqi
author_facet Li, Zehao
Yu, Hongwei
Jiang, Hao
Sheng, Qiang
Xu, Yilong
Bi, Baolong
Li, Yang
Yuan, Zhenlong
Cai, Yujun
Wang, Zhaoqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22963
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
Li, Zehao
Yu, Hongwei
Jiang, Hao
Sheng, Qiang
Xu, Yilong
Bi, Baolong
Li, Yang
Yuan, Zhenlong
Cai, Yujun
Wang, Zhaoqi
Artificial Intelligence
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.
title FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2602.22963