# OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning

arXiv: https://arxiv.org/abs/2604.17052 · HTML: https://mlsanity.com/paper/2604.17052/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 58 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 29 of 29)

- [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)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [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)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output](https://mlsanity.com/paper/2407.03320/) (2024)
- [Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2406.08085/) (2024)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension](https://mlsanity.com/paper/2411.13093/) (2024)
- [Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input](https://mlsanity.com/paper/2408.15542/) (2024)
- [Large Multimodal Agents: A Survey](https://mlsanity.com/paper/2402.15116/) (2024)
- [Frame-Voyager: Learning to Query Frames for Video Large Language Models](https://mlsanity.com/paper/2410.03226/) (2024)
- [Flash-VStream: Efficient Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2506.23825/) (2025)
- [Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge](https://mlsanity.com/paper/2501.13468/) (2025)
- [SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding](https://mlsanity.com/paper/2502.10810/) (2025)
- [VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning](https://mlsanity.com/paper/2503.13444/) (2025)
- [FreeVA: Offline MLLM as Training-Free Video Assistant](https://mlsanity.com/paper/2405.07798/) (2024)
- [Enhancing Long Video Understanding via Hierarchical Event-Based Memory](https://mlsanity.com/paper/2409.06299/) (2024)
- [Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understanding](https://mlsanity.com/paper/2505.23990/) (2025)
- [Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding](https://mlsanity.com/paper/2508.09486/) (2025)
- [WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs](https://mlsanity.com/paper/2408.07611/) (2024)
- [CogStream: Context-guided Streaming Video Question Answering](https://mlsanity.com/paper/2506.10516/) (2025)

## Built on by (most cited first, 19 of 19)

- [ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding](https://mlsanity.com/paper/2607.28312/) (2026)
- [StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs](https://mlsanity.com/paper/2608.13416/) (2026)
- [FOLIO: Focused Semantic Memory for Streaming Video Understanding](https://mlsanity.com/paper/2607.13298/) (2026)
- [StreamScout: Learning When to Look Deeper for Streaming Video Understanding](https://mlsanity.com/paper/2609.00291/) (2026)
- [GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience](https://mlsanity.com/paper/2608.02392/) (2026)
- [ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding](https://mlsanity.com/paper/2609.02780/) (2026)
- [StreamFlow: Dynamic Memory Flows for Streaming Video Understanding](https://mlsanity.com/paper/2608.10949/) (2026)
- [EM^2Mem: Event-Centric Multimodal Memory for Large Language Models](https://mlsanity.com/paper/2609.00551/) (2026)
- [Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding](https://mlsanity.com/paper/2609.04131/) (2026)
- [SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning](https://mlsanity.com/paper/2608.07959/) (2026)
- [Search over the Visual World: Persistent Visual Memory, Layered Indexes, and Source-Grounded Evidence](https://mlsanity.com/paper/2608.08075/) (2026)
- [MemEvo: Automatic Discovery of Streaming Video Memory Mechanisms](https://mlsanity.com/paper/2609.36581/) (2026)
- [Simple Agentic Memory for Generalist Robot Policies](https://mlsanity.com/paper/2609.36595/) (2026)
- [When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs](https://mlsanity.com/paper/2609.37345/) (2026)
- [APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants](https://mlsanity.com/paper/2609.37559/) (2026)
- [FlashBack: Knowing When to Remember in Streaming Vision-Language Models](https://mlsanity.com/paper/2610.01192/) (2026)
- [ReMem: Streaming Video Understanding With Long Context Retention](https://mlsanity.com/paper/2610.05940/) (2026)
- [EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos](https://mlsanity.com/paper/2610.17128/) (2026)
- [DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding](https://mlsanity.com/paper/2610.19849/) (2026)

## Abstract (arXiv)

Streaming video reasoning requires models to operate in a setting where history grows without bound while meaningful evidence remains scarce. In such a landscape, relevant signal is like an oasis-small, critical, and easily lost in a desert of redundancy. Enlarging memory only widens the desert; aggressive compression dries up the oasis. The real difficulty lies in discovering where to look, not how much to remember. We therefore introduce OASIS, a novel framework for streaming video reasoning that tackles this challenge through structured, on-demand retrieval. It organizes streaming history into hierarchical events and performs reasoning as controlled refinement-short-context inference first, followed by semantically grounded retrieval only when uncertainty arises. As the retrieval is driven by high-level intent rather than embedding similarity, the retrieved memory is substantially more accurate and less noisy. Additionally, the mechanism is plug-and-play, training-free, and readily attaches to different streaming MLLM backbones. Experiments across multiple benchmarks and backbones show that OASIS achieves strong gains in long-horizon accuracy and compositional reasoning with bounded token cost and low request delay. Code is available at https://github.com/Solus-sano/OASIS.