# Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?

arXiv: https://arxiv.org/abs/2609.17248 · HTML: https://mlsanity.com/paper/2609.17248/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos](https://mlsanity.com/paper/2501.13826/) (2025)
- [VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction](https://mlsanity.com/paper/2501.01957/) (2025)
- [MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding](https://mlsanity.com/paper/2406.14515/) (2024)
- [VITA: Towards Open-Source Interactive Omni Multimodal LLM](https://mlsanity.com/paper/2408.05211/) (2024)
- [WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs](https://mlsanity.com/paper/2502.04326/) (2025)
- [MMVU: Measuring Expert-Level Multi-Discipline Video Understanding](https://mlsanity.com/paper/2501.12380/) (2025)
- [Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?](https://mlsanity.com/paper/2505.21374/) (2025)
- [video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models](https://mlsanity.com/paper/2406.15704/) (2024)
- [Video Question Answering: Datasets, Algorithms and Challenges](https://mlsanity.com/paper/2203.01225/) (2022)
- [OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs](https://mlsanity.com/paper/2510.10689/) (2025)
- [VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning](https://mlsanity.com/paper/2503.13444/) (2025)
- [VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning](https://mlsanity.com/paper/2504.07956/) (2025)
- [InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue](https://mlsanity.com/paper/2510.13747/) (2025)
- [A Survey of Token Compression for Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2507.20198/) (2025)
- [OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models](https://mlsanity.com/paper/2511.14582/) (2025)
- [Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes](https://mlsanity.com/paper/2506.09557/) (2025)
- [Guiding the Inner Eye: A Framework for Hierarchical and Flexible Visual Grounded Reasoning](https://mlsanity.com/paper/2511.22172/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient context processing. Existing benchmarks over-rely on visual heuristics while marginalizing auditory cues, effectively reducing models to "silent observers" that bypass genuine cross-modal reasoning. Moreover, standard dense sampling creates an evidence-context trade-off: increasing frames to capture evidence inevitably leads to attention distraction and token explosion. To bridge these gaps, we present Video-HolmesV2, a novel benchmark designed for Deep Audio-Visual Coupling. Unlike previous works, it enforces an Evidence-Based Evaluation, requiring models to justify answers with precise spatio-temporal audio-visual evidence, thereby reducing confounding effects of guessing and hallucinated evidence. To support this, we introduce: (1) a Multi-Model Cross-Verification pipeline to ensure task rigor; (2) a Spatio-temporal Evidence-Aware Metric for fine-grained calibration. Furthermore, we propose an Audio-Text Guided Token Compression framework. By fusing task intent with auditory anchors, our method distills high-value reasoning cues to mitigate long-context noise. In our evaluation, even strong proprietary models achieve below 60% accuracy, while our approach outperforms comparable open-source omni-models.