Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection

Source

Source name: arXiv
Source kind: paper
Authors / organization: Haochen Zhao, Yongxiu Xu, Xinkui Lin, Dong Xie, Jiarui Lu, Yuqi Qian, Yubin Wang, Hongbo Xu, Gaopeng Gou
Venue: arXiv: cs.CV
Published: 2026-07-20
Collected: 2026-07-21
URL: http://arxiv.org/abs/2607.18080v1
PDF: https://arxiv.org/pdf/2607.18080v1
DOI: UNKNOWN

Plain-Language Brief

Researchers propose SIEVE, a framework for detecting video misinformation by first identifying key pieces of evidence that contribute to the decision, and then verifying the veracity based on these identified pieces. The framework uses an evidence-seeking agent that learns from supervised evidence-seeking trajectories and an evidence-aware reinforcement learning objective.

What the Document Says

The paper presents SIEVE, a framework for sparse interactive evidence verification in multimodal video misinformation detection.
The proposed framework consists of an evidence-seeking agent and a verifier.
The evidence-seeking agent explores the available multimodal evidence to construct a compact evidence package.
The verifier uses this evidence package to determine veracity.
The agent is trained with supervised evidence-seeking trajectories and an evidence-aware reinforcement learning objective.
Experiments show that SIEVE outperforms evaluated baselines and provides an explicit and inspectable evidence trail, improving transparency.
The aim is to reduce redundancy in exhaustive multimodal reasoning by decoupling evidence acquisition from verification.

Key Concepts Mentioned

multimodal video misinformation detection
SIEVE framework
evidence-seeking agent
verifier
supervised learning
reinforcement learning
experiments
transparency

Claims Made by the Document

SIEVE outperforms evaluated baselines.
The resulting acquisition process improves transparency.

Evidence Used

Experiments on multiple video misinformation benchmarks

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Multimodal video misinformation detection is commonly formulated as a holistic video-understanding task, where the entire video and its associated content are processed and judged in a single pass. However, real-world misinformation often exhibits a sparse and compositional evidence structure: a reliable decision may depend on only a few coupled clues, while most video content contributes limited additional information. Exhaustive multimodal reasoning may therefore introduce substantial redundancy and obscure decisive evidence. This motivates decoupling evidence acquisition from verification: first identifying sparse, decision-relevant clues and then judging veracity based on the acquired evidence. Accordingly, we propose SIEVE, a framework for Sparse Interactive Evidence Verification via Extraction in multimodal video misinformation detection. An evidence-seeking agent actively explores the available multimodal evidence and constructs a compact evidence package, which is then used by a verifier to determine veracity. The agent is trained with supervised evidence-seeking trajectories and an evidence-aware reinforcement learning objective that promotes informative evidence acquisition while discouraging unnecessary or invalid interactions. Experiments on multiple video misinformation benchmarks show that SIEVE consistently outperforms the evaluated baselines and supports reliable verification using compact evidence packages. Moreover, the resulting acquisition process provides an explicit and inspectable evidence trail, improving the transparency and groundedness of multimodal misinformation detection.