Papers
arxiv:2512.03500

EEA: Exploration-Exploitation Agent for Long Video Understanding

Published on Dec 3
Authors:
,
,
,
,
,

Abstract

EEA, a novel video agent framework, achieves balanced exploration and exploitation in long-form video understanding through semantic guidance and hierarchical tree search, combining vision-language models with semantic priors to enhance performance and efficiency.

AI-generated summary

Long-form video understanding requires efficient navigation of extensive visual data to pinpoint sparse yet critical information. Current approaches to longform video understanding either suffer from severe computational overhead due to dense preprocessing, or fail to effectively balance exploration and exploitation, resulting in incomplete information coverage and inefficiency. In this work, we introduce EEA, a novel video agent framework that archives exploration-exploitation balance through semantic guidance with hierarchical tree search process. EEA autonomously discovers and dynamically updates task-relevant semantic queries, and collects video frames closely matched to these queries as semantic anchors. During the tree search process, instead of uniform expansion, EEA preferentially explores semantically relevant frames while ensuring sufficient coverage within unknown segments. Moreover, EEA adaptively combines intrinsic rewards from visionlanguage models (VLMs) with semantic priors by explicitly modeling uncertainty to achieve stable and precise evaluation of video segments. Experiments across various long-video benchmarks validate the superior performance and computational efficiency of our proposed method.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2512.03500 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2512.03500 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2512.03500 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.