# Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

arXiv: https://arxiv.org/abs/2512.05774 · HTML: https://mlsanity.com/paper/2512.05774/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 61 of its 77 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 61)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding](https://mlsanity.com/paper/2403.11481/) (2024)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding](https://mlsanity.com/paper/2409.14485/) (2024)
- [Self-Chained Image-Language Model for Video Localization and Question Answering](https://mlsanity.com/paper/2305.06988/) (2023)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [A Simple LLM Framework for Long-Range Video Question-Answering](https://mlsanity.com/paper/2312.17235/) (2023)
- [Revisiting the "Video" in Video-Language Understanding](https://mlsanity.com/paper/2206.01720/) (2022)
- [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025)
- [Tarsier: Recipes for Training and Evaluating Large Video Description Models](https://mlsanity.com/paper/2407.00634/) (2024)
- [Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension](https://mlsanity.com/paper/2411.13093/) (2024)
- [HourVideo: 1-Hour Video-Language Understanding](https://mlsanity.com/paper/2411.04998/) (2024)
- [End-to-end Learning of Action Detection from Frame Glimpses in Videos](https://mlsanity.com/paper/1511.06984/) (2015)
- [Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding](https://mlsanity.com/paper/2505.18079/) (2025)
- [VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning](https://mlsanity.com/paper/2505.12434/) (2025)

## Built on by (most cited first, 29 of 29)

- [Active Perception Agent for Omnimodal Audio-Video Understanding](https://mlsanity.com/paper/2512.23646/) (2025)
- [EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding](https://mlsanity.com/paper/2605.09874/) (2026)
- [OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering](https://mlsanity.com/paper/2602.03707/) (2026)
- [Watch, Remember, Reason: Human-View Video Understanding with MLLMs](https://mlsanity.com/paper/2606.07433/) (2026)
- [Personal Visual Context Learning in Large Multimodal Models](https://mlsanity.com/paper/2605.10936/) (2026)
- [Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning](https://mlsanity.com/paper/2605.28192/) (2026)
- [Multimodal Fact-Level Attribution for Verifiable Reasoning](https://mlsanity.com/paper/2602.11509/) (2026)
- [Towards Sparse Video Understanding and Reasoning](https://mlsanity.com/paper/2602.13602/) (2026)
- [VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding](https://mlsanity.com/paper/2603.22285/) (2026)
- [TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding](https://mlsanity.com/paper/2608.22516/) (2026)
- [TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos](https://mlsanity.com/paper/2605.07593/) (2026)
- [Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval](https://mlsanity.com/paper/2605.23826/) (2026)
- [Benchmarking Visual State Tracking in Multimodal Video Understanding](https://mlsanity.com/paper/2606.03920/) (2026)
- [Rethinking RAG in Long Videos: What to Retrieve and How to Use It?](https://mlsanity.com/paper/2606.13141/) (2026)
- [Agents in the Large: Perception-Centered Architecture for Persistent Agents](https://mlsanity.com/paper/2608.30478/) (2026)
- [TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living](https://mlsanity.com/paper/2606.20561/) (2026)
- [Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA](https://mlsanity.com/paper/2607.16189/) (2026)
- [FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding](https://mlsanity.com/paper/2607.25266/) (2026)
- [Conditional Visual Evidence Utility: State-Dependent Rank Reversals in Frozen Vision-Language Encoders](https://mlsanity.com/paper/2608.28316/) (2026)
- [VideoResearcher: Self-Improving Tool Design for Long-Video Understanding](https://mlsanity.com/paper/2609.19664/) (2026)
- [INSPECT: Learning Robot View Selection from Assistant Use](https://mlsanity.com/paper/2609.20615/) (2026)
- [AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents](https://mlsanity.com/paper/2609.21386/) (2026)
- [S4VY: Segment Anything in Feed-Forward 4D Visual Geometry](https://mlsanity.com/paper/2609.36875/) (2026)
- [Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies](https://mlsanity.com/paper/2609.38155/) (2026)
- [LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception](https://mlsanity.com/paper/2609.39938/) (2026)
- [Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering](https://mlsanity.com/paper/2610.00757/) (2026)
- [CASE: Cost-Aware Stopping for Efficient Long-Video Agents](https://mlsanity.com/paper/2610.05400/) (2026)
- [Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction](https://mlsanity.com/paper/2610.12984/) (2026)
- [Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering](https://mlsanity.com/paper/2610.20085/) (2026)

## Abstract (arXiv)

Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried in hours of mostly redundant and irrelevant content. While agentic pipelines improve video reasoning capabilities, prevailing frameworks rely on a query-agnostic captioner to perceive video information, which wastes computation on irrelevant content and blurs fine-grained temporal and spatial information. Motivated by active perception theory, we argue that LVU agents should actively decide what, when, and where to observe, and continuously assess whether the current observation is sufficient to answer the query. We present Active Video Perception (AVP), an evidence-seeking framework that treats the video as an interactive environment and acquires compact, queryrelevant evidence directly from pixels. Concretely, AVP runs an iterative plan-observe-reflect process with MLLM agents. In each round, a planner proposes targeted video interactions, an observer executes them to extract time-stamped evidence, and a reflector evaluates the sufficiency of the evidence for the query, either halting with an answer or triggering further observation. Across five LVU benchmarks, AVP achieves highest overall accuracy with significant improvements. Notably, AVP outperforms the best agentic method by 5.7% in average overall accuracy while only requires 18.4% inference time and 12.4% input tokens.