LensWalk: Agentic Video Understanding by Planning How You See in Videos

• URL: http://arxiv.org/abs/2603.24558v1
• Date: Wed, 25 Mar 2026 17:38:54 GMT
• Title: LensWalk: Agentic Video Understanding by Planning How You See in Videos
• Abstract summary: We introduce LensWalk, a flexible agentic framework that empowers a Large Language Model reasoner to control its own visual observation actively.<n>LensWalk establishes a tight reason-plan-observe loop where the agent dynamically specifies, at each step, the temporal scope and sampling density of the video it observes.
• Score: 45.81048261339695
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods for video understanding are limited by the inherent disconnect between reasoning and perception: they rely on static, pre-processed information and cannot actively seek raw evidence from video as their understanding evolves. To address this, we introduce LensWalk, a flexible agentic framework that empowers a Large Language Model reasoner to control its own visual observation actively. LensWalk establishes a tight reason-plan-observe loop where the agent dynamically specifies, at each step, the temporal scope and sampling density of the video it observes. Using a suite of versatile, Vision-Language Model based tools parameterized by these specifications, the agent can perform broad scans for cues, focus on specific segments for fact extraction, and stitch evidence from multiple moments for holistic verification. This design allows for progressive, on-demand evidence gathering that directly serves the agent's evolving chain of thought. Without requiring any model fine-tuning, LensWalk delivers substantial, plug-and-play performance gains on multiple model recipes, boosting their accuracy by over 5\% on challenging long-video benchmarks like LVBench and Video-MME. Our analysis reveals that enabling an agent to control how it sees is key to unlocking more accurate, robust, and interpretable video reasoning.

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)
• VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation [46.226603529472065]
  VideoSeeker is a novel paradigm for instance-level video understanding through visual prompts.<n>We construct a four-stage fully automated data synthesis pipeline to efficiently generate large-scale, high-quality instance-level video data.<n>Our model achieves an average improvement of +13.7% over baselines on instance-level video understanding tasks.
  arXiv  Detail & Related papers  (2026-05-15T15:43:28Z)
• VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking [49.09710846673772]
  VideoSeek is a video agent that actively seeks answer-critical evidence instead of exhaustively parsing the full video.<n>VideoSeek operates in a think-act-observe loop with a well-designed toolkit for collecting multi-granular video observations.
  arXiv  Detail & Related papers  (2026-03-20T17:58:47Z)
• VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning [36.3278051400066]
  VideoThinker is an agentic Video Large Language Model trained entirely on synthetic tool interaction trajectories.<n>Our key idea is to convert videos into rich captions and employ a powerful agentic language model to generate multi-step tool use sequences in caption space.<n>Training on this synthetic agentic dataset equips VideoThinker with dynamic reasoning capabilities, adaptive temporal exploration, and multi-step tool use.
  arXiv  Detail & Related papers  (2026-01-22T07:47:29Z)
• VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning [49.35834435935727]
  VideoZoomer is a novel agentic framework that enables MLLMs to control their visual focus during reasoning.<n>Our 7B model delivers diverse and complex reasoning patterns, yielding strong performance across a broad set of long video understanding and reasoning benchmarks.<n>These emergent capabilities allow it to consistently surpass existing open-source models and even rival proprietary systems on challenging tasks.
  arXiv  Detail & Related papers  (2025-12-26T11:43:21Z)
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models [56.851611990473174]
  Reasoning over dynamic visual content remains a central challenge for large language models.<n>We propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency.<n>The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T18:59:58Z)
• 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)
• VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning [33.37714717781103]
  VideoMind is a novel video-language agent designed for temporal-grounded video understanding.<n>We identify essential capabilities for video temporal reasoning and develop a role-based agentic workflow.<n>We propose a novel Chain-of-LoRA strategy, enabling seamless role-switching via lightweight LoRA adaptors.
  arXiv  Detail & Related papers  (2025-03-17T17:59:33Z)
• Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering [71.62961521518731]
  HeurVidQA is a framework that leverages domain-specific entity-actions to refine pre-trained video-language foundation models. Our approach treats these models as implicit knowledge engines, employing domain-specific entity-action prompters to direct the model's focus toward precise cues that enhance reasoning.
  arXiv  Detail & Related papers  (2024-10-12T06:22:23Z)

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.