EEA: Exploration-Exploitation Agent for Long Video Understanding

• URL: http://arxiv.org/abs/2512.03500v1
• Date: Wed, 03 Dec 2025 06:48:36 GMT
• Title: EEA: Exploration-Exploitation Agent for Long Video Understanding
• Abstract summary: Long-form video understanding requires efficient navigation of extensive visual data to pinpoint sparse yet critical information.<n>Current approaches to longform video understanding either suffer from severe computational overhead due to dense preprocessing.<n>We introduce EEA, a novel video agent framework that archives exploration-exploitation balance through semantic guidance.
• Score: 24.45791994592314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding [61.00809248898572]
  Long video understanding is a problem in which an agent reads the video turn by turn along the temporal axis, deciding at each turn how fast to watch, what evidence to retain, when to revisit uncertain segments, and when to stop and answer.<n>We propose textbfVideoScout, a multi-turn reasoning agent that instantiates the SEA paradigm through adaptive reasoning pacing.<n>Experiments on long video understanding and reasoning benchmarks demonstrate that our 7B model achieves strong performance compared with existing trained 7B agentic models.
  arXiv  Detail & Related papers  (2026-09-14T14:04:03Z)
• MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding [11.308633179211348]
  textbfMAVIS is a novel multi-agent framework that rethinks retrieval as cooperative reasoning rather than brute-force search.<n>During retrieval, a planner decomposes complex user intents into atomic sub-tasks, dispatching specialized agents to independently nominate candidates.<n>Experiments on MSR-VTT, MSVD, and ActivityNet demonstrate that MAVIS achieves competitive performance without task-specific fine-tuning.
  arXiv  Detail & Related papers  (2026-06-08T15:36:15Z)
• CACR:Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning [8.230031783815749]
  TAGV aims to locate precise video segments that respond to natural language queries.<n>This task remains challenging due to the need to comprehend semantically complex questions.<n>We propose a Candidate-Aware Causal Reasoning framework to tackle these limitations.
  arXiv  Detail & Related papers  (2026-06-07T03:23:18Z)
• Explainable Forensics of Manipulated Segments in Untrimmed Long Videos [50.190474724159465]
  We formulate the task of Temporal AI-Generated Segment localization and Explanation.<n>We introduce TASLE, a large-scale benchmark comprising 12,472 untrimmed videos with diverse manipulation patterns and rich annotation signals.<n>We propose MSLoc, a coarse-to-fine forensic baseline that combines a boundary-sensitive proposal generation module for efficient long-video scanning with an MLLM-based refinement module for precise boundary localization and interpretable reasoning.
  arXiv  Detail & Related papers  (2026-06-01T15:48:38Z)
• Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA Challenge [9.253622130813044]
  We propose a unified framework that decouples long-video reasoning into two complementary forms of evidence: semantic evidence and visual evidence.<n>Our results demonstrate that explicitly structuring, retrieving, and integrating semantic and visual evidence is critical for effective long-video understanding with MLLMs.
  arXiv  Detail & Related papers  (2026-05-28T05:53:34Z)
• Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search [61.88597038104749]
  We present HAVEN, a unified framework for long-video understanding that enables coherent and comprehensive reasoning.<n>We preserve semantic consistency by integrating entity-level representations across visual and auditory streams.<n>We employ an agentic search mechanism to enable dynamic retrieval and reasoning across these layers.
  arXiv  Detail & Related papers  (2026-01-20T08:23:29Z)
• SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding [36.30263540665245]
  We propose a framework for effective and reliable long video understanding.<n>SeViCES is training-free and model-agnostic, and introduces two key components.<n> experiments on long video understanding benchmarks show that SeViCES consistently outperforms state-of-the-art methods in both accuracy and robustness.
  arXiv  Detail & Related papers  (2025-10-23T14:55:28Z)
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
  We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-04T21:48:40Z)
• AHA - Predicting What Matters Next: Online Highlight Detection Without Looking Ahead [4.55107996328448]
  Aha is an autoregressive highlight detection framework that predicts relevance of each video frame against a task described in natural language.<n>Aha achieves state-of-the-art (SOTA) performance on highlight detection benchmarks.<n>We explore Aha's potential for real-world robotics applications given a task-oriented natural language input and a continuous, robot-centric video.
  arXiv  Detail & Related papers  (2025-09-19T21:03:00Z)
• AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding [73.60257070465377]
  AdaVideoRAG is a novel framework that adapts retrieval based on query complexity using a lightweight intent classifier.<n>Our framework employs an Omni-Knowledge Indexing module to build hierarchical databases from text (captions, ASR, OCR), visual features, and semantic graphs.<n> Experiments demonstrate improved efficiency and accuracy for long-video understanding, with seamless integration into existing MLLMs.
  arXiv  Detail & Related papers  (2025-06-16T15:18:15Z)
• VideoExplorer: Think With Videos For Agentic Long-Video Understanding [117.68219930263153]
  Long-video understanding is a challenging problem in computer vision.<n>We propose VideoExplorer, a framework grounded in the principle of thinking with video''<n>Rather than reasoning over a static context, VideoExplorer iteratively formulates sub-questions, locates relevant moments, and performs task-oriented, temporally scalable video understanding.
  arXiv  Detail & Related papers  (2025-06-12T15:39:10Z)
• Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding [60.88843818016968]
  Long-form video understanding presents significant challenges due to temporal-spatial complexity and difficulty of question answering.<n>We propose the Deep Video Discovery (DVD) agent to leverage an agentic search strategy over segmented video clips.<n>Our DVD agent achieves state-of-the-art performance on the challenging LVBench dataset, reaching an accuracy of 74.2%.
  arXiv  Detail & Related papers  (2025-05-23T16:37:36Z)
• Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning [56.873534081386]
  A new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning.<n>We propose a query-centric audio-visual cognition network to construct a reliable multi-modal representation for three tasks.<n>This can cognize user-preferred content and thus attain a query-centric audio-visual representation for three tasks.
  arXiv  Detail & Related papers  (2024-12-18T06:43:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.