Research

Paper

TESTING March 05, 2026

Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding

Authors

Zheng Wang, Haoran Chen, Haoxuan Qin, Zhipeng Wei, Tianwen Qian, Cong Bai

Abstract

Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumulate semantic drift and correlation-driven errors. We argue that long-video reasoning should begin not with reactive retrieval, but with deliberate task formulation: the model must first articulate what must be true in the video for each candidate answer to hold. This thinking-before-finding principle motivates VideoHV-Agent, a framework that reformulates video question answering as a structured hypothesis-verification process. Based on video summaries, a Thinker rewrites answer candidates into testable hypotheses, a Judge derives a discriminative clue specifying what evidence must be checked, a Verifier grounds and tests the clue using localized, fine-grained video content, and an Answer agent integrates validated evidence to produce the final answer. Experiments on three long-video understanding benchmarks show that VideoHV-Agent achieves state-of-the-art accuracy while providing enhanced interpretability, improved logical soundness, and lower computational cost. We make our code publicly available at: https://github.com/Haorane/VideoHV-Agent.

Metadata

arXiv ID: 2603.04977
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-05
Fetched: 2026-03-06 14:20

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.04977v1</id>\n    <title>Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding</title>\n    <updated>2026-03-05T09:16:07Z</updated>\n    <link href='https://arxiv.org/abs/2603.04977v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.04977v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumulate semantic drift and correlation-driven errors. We argue that long-video reasoning should begin not with reactive retrieval, but with deliberate task formulation: the model must first articulate what must be true in the video for each candidate answer to hold. This thinking-before-finding principle motivates VideoHV-Agent, a framework that reformulates video question answering as a structured hypothesis-verification process. Based on video summaries, a Thinker rewrites answer candidates into testable hypotheses, a Judge derives a discriminative clue specifying what evidence must be checked, a Verifier grounds and tests the clue using localized, fine-grained video content, and an Answer agent integrates validated evidence to produce the final answer. Experiments on three long-video understanding benchmarks show that VideoHV-Agent achieves state-of-the-art accuracy while providing enhanced interpretability, improved logical soundness, and lower computational cost. We make our code publicly available at: https://github.com/Haorane/VideoHV-Agent.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-05T09:16:07Z</published>\n    <arxiv:comment>Accepted at CVPR 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Zheng Wang</name>\n    </author>\n    <author>\n      <name>Haoran Chen</name>\n    </author>\n    <author>\n      <name>Haoxuan Qin</name>\n    </author>\n    <author>\n      <name>Zhipeng Wei</name>\n    </author>\n    <author>\n      <name>Tianwen Qian</name>\n    </author>\n    <author>\n      <name>Cong Bai</name>\n    </author>\n  </entry>"
}