# When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs

arXiv: https://arxiv.org/abs/2609.37345 · HTML: https://mlsanity.com/paper/2609.37345/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 38 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 30 of 36)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [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)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [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)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [MLVU: Benchmarking Multi-task Long Video Understanding](https://mlsanity.com/paper/2406.04264/) (2024)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?](https://mlsanity.com/paper/2501.05510/) (2025)
- [Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction](https://mlsanity.com/paper/2501.03218/) (2025)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos](https://mlsanity.com/paper/2504.17343/) (2025)
- [Flash-VStream: Efficient Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2506.23825/) (2025)
- [StreamForest: Efficient Online Video Understanding with Persistent Event Memory](https://mlsanity.com/paper/2509.24871/) (2025)
- [Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge](https://mlsanity.com/paper/2501.13468/) (2025)
- [Online Video Understanding: OVBench and VideoChat-Online](https://mlsanity.com/paper/2501.00584/) (2024)
- [LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval](https://mlsanity.com/paper/2505.15269/) (2025)
- [StreamingTOM: Streaming Token Compression for Efficient Video Understanding](https://mlsanity.com/paper/2510.18269/) (2025)
- [HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding](https://mlsanity.com/paper/2601.14724/) (2026)
- [Accelerating Streaming Video Large Language Models via Hierarchical Token Compression](https://mlsanity.com/paper/2512.00891/) (2025)
- [A Simple Baseline for Streaming Video Understanding](https://mlsanity.com/paper/2604.02317/) (2026)

## Abstract (arXiv)

Streaming video understanding requires Video Large Language Models (Video-LLMs) to reason over continuous visual streams under causal constraints. As the visual history grows, a bounded visual?processing budget requires evidence selection that balances temporal recency with query relevance. Recent-only selection excludes potentially relevant historical evidence, whereas Semantic-only retrieval can displace useful recent context when relevance scores are ambiguous. We introduce WRWS (When to Retrieve, When to Stay), a training-free framework for uncertainty-adaptive evidence allocation. A lightweight external vision-language encoder scores query relevance across the observed history, while an adaptive allocation module uses the normalized entropy of the similarity distribution as a proxy for retrieval uncertainty. WRWS favors semantic retrieval when relevance cues are reliable and strengthens the recency prior under uncertainty. Following a retrieve-first, encode-later pipeline, WRWS selects evidence before target-model visual encoding, such that only the selected observations are processed by the costly target Video-LLM. Experiments across four Video-LLM families and multiple model scales demonstrate competitive accuracy on StreamingBench and OVO-Bench. In our efficiency evaluation, WRWS reduces average vision-to-answer time to 47.93% of the state-of-the-art method. Code will be released.