# VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding

arXiv: https://arxiv.org/abs/2512.12360 · HTML: https://mlsanity.com/paper/2512.12360/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 38 of its 42 references that are in the map.
- First posted on arXiv 13 Dec 2025.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (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)
- [mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models](https://mlsanity.com/paper/2408.04840/) (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)
- [MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding](https://mlsanity.com/paper/2404.05726/) (2024)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling](https://mlsanity.com/paper/2501.12386/) (2025)
- [A Simple LLM Framework for Long-Range Video Question-Answering](https://mlsanity.com/paper/2312.17235/) (2023)
- [Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding](https://mlsanity.com/paper/2505.18079/) (2025)
- [DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models](https://mlsanity.com/paper/2411.15024/) (2024)
- [Audio-Visual LLM for Video Understanding](https://mlsanity.com/paper/2312.06720/) (2023)
- [LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents](https://mlsanity.com/paper/2503.10200/) (2025)
- [VideoRAG: Retrieval-Augmented Generation over Video Corpus](https://mlsanity.com/paper/2501.05874/) (2025)
- [VCA: Video Curious Agent for Long Video Understanding](https://mlsanity.com/paper/2412.10471/) (2024)
- [AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding](https://mlsanity.com/paper/2503.12559/) (2025)
- [Large Language Models are Strong Audio-Visual Speech Recognition Learners](https://mlsanity.com/paper/2409.12319/) (2024)

## Built on by (most cited first, 25 of 25)

- [LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs](https://mlsanity.com/paper/2603.19217/) (2026)
- [OmniGAIA: Towards Native Omni-Modal AI Agents](https://mlsanity.com/paper/2602.22897/) (2026)
- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework](https://mlsanity.com/paper/2603.11768/) (2026)
- [Active Perception Agent for Omnimodal Audio-Video Understanding](https://mlsanity.com/paper/2512.23646/) (2025)
- [MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism](https://mlsanity.com/paper/2606.07512/) (2026)
- [Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval](https://mlsanity.com/paper/2605.16481/) (2026)
- [PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search](https://mlsanity.com/paper/2606.03099/) (2026)
- [MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding](https://mlsanity.com/paper/2608.04587/) (2026)
- [Progressive Video Condensation with MLLM Agent for Long-form Video Understanding](https://mlsanity.com/paper/2604.02891/) (2026)
- [AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding](https://mlsanity.com/paper/2608.03779/) (2026)
- [Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding](https://mlsanity.com/paper/2608.20805/) (2026)
- [Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding](https://mlsanity.com/paper/2609.11899/) (2026)
- [VideoAtlas: Navigating Long-Form Video in Logarithmic Compute](https://mlsanity.com/paper/2603.17948/) (2026)
- [ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding](https://mlsanity.com/paper/2605.13228/) (2026)
- [Conditional Multi-Event Temporal Grounding in Long-Form Video](https://mlsanity.com/paper/2606.15320/) (2026)
- [EM^2Mem: Event-Centric Multimodal Memory for Large Language Models](https://mlsanity.com/paper/2609.00551/) (2026)
- [GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory](https://mlsanity.com/paper/2606.06532/) (2026)
- [From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents](https://mlsanity.com/paper/2608.31005/) (2026)
- [VideoResearcher: Self-Improving Tool Design for Long-Video Understanding](https://mlsanity.com/paper/2609.19664/) (2026)
- [Agentic Video Understanding: A Survey](https://mlsanity.com/paper/2609.31713/) (2026)
- [Simple Agentic Memory for Generalist Robot Policies](https://mlsanity.com/paper/2609.36595/) (2026)
- [VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents](https://mlsanity.com/paper/2609.38119/) (2026)
- [MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories](https://mlsanity.com/paper/2609.40195/) (2026)
- [VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding](https://mlsanity.com/paper/2610.11171/) (2026)

## Abstract (arXiv)

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming video preprocessing to guide MLLMs in autonomous reasoning. To overcome these limitations, we introduce VideoARM, an Agentic Reasoning-over-hierarchical-Memory paradigm for long-form video understanding. Instead of static, exhaustive preprocessing, VideoARM performs adaptive, on-the-fly agentic reasoning and memory construction. Specifically, VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner, thereby substantially reducing token consumption. In parallel, a hierarchical multimodal memory continuously captures and updates multi-level clues throughout the operation of the agent, providing precise contextual information to support the controller in decision-making. Experiments on prevalent benchmarks demonstrate that VideoARM outperforms the state-of-the-art method, DVD, while significantly reducing token consumption for long-form videos.