# CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning

arXiv: https://arxiv.org/abs/2508.19542 · HTML: https://mlsanity.com/paper/2508.19542/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Placed in

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

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [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)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models](https://mlsanity.com/paper/2311.16103/) (2023)
- [Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity](https://mlsanity.com/paper/2412.06171/) (2024)
- [LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos](https://mlsanity.com/paper/2411.19772/) (2024)
- [AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering](https://mlsanity.com/paper/2311.14906/) (2023)
- [LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models](https://mlsanity.com/paper/2408.14008/) (2024)
- [STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding](https://mlsanity.com/paper/2503.15973/) (2025)
- [MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval](https://mlsanity.com/paper/2406.17880/) (2024)
- [V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents](https://mlsanity.com/paper/2503.12077/) (2025)
- [Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs](https://mlsanity.com/paper/2504.00072/) (2025)
- [New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration](https://mlsanity.com/paper/2502.20104/) (2025)

## Built on by (most cited first, 16 of 16)

- [SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning](https://mlsanity.com/paper/2606.13673/) (2026)
- [ERNIE 5.0 Technical Report](https://mlsanity.com/paper/2602.04705/) (2026)
- [Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams](https://mlsanity.com/paper/2606.15200/) (2026)
- [Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces](https://mlsanity.com/paper/2602.07864/) (2026)
- [Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos](https://mlsanity.com/paper/2603.17693/) (2026)
- [Improving MoE Compute Efficiency by Composing Weight and Data Sparsity](https://mlsanity.com/paper/2601.15370/) (2026)
- [AgentCVR: Active Multi-Agent Cross-Video Reasoning via Script-Simulated Reinforcement Learning](https://mlsanity.com/paper/2605.29643/) (2026)
- [FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2510.11190/) (2025)
- [Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM Training](https://mlsanity.com/paper/2603.04415/) (2026)
- [A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding](https://mlsanity.com/paper/2603.14733/) (2026)
- [SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models](https://mlsanity.com/paper/2604.16883/) (2026)
- [SYNCR: A Cross-Video Reasoning Benchmark with Synthetic Grounding](https://mlsanity.com/paper/2605.08412/) (2026)
- [SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs via Task-Oriented Visual Supervision](https://mlsanity.com/paper/2606.19915/) (2026)
- [SYNCR: Diagnosing and Learning Cross-Video Reasoning from Simulation](https://mlsanity.com/paper/2609.37918/) (2026)
- [Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning](https://mlsanity.com/paper/2610.03099/) (2026)
- [Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoning](https://mlsanity.com/paper/2610.05023/) (2026)

## Abstract (arXiv)

While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their capability for spatiotemporal pattern reasoning across multiple videos remains a critical gap in pattern recognition research. However, this capability is essential for real-world applications, including multi-camera surveillance and cross-video procedural learning. To bridge this gap, we present CVBench, the first diagnostic benchmark designed to assess cross-video relational reasoning rigorously. CVBench comprises 1,000 question-answer pairs spanning three hierarchical tiers: cross-video object association (identifying shared entities), cross-video event association (linking temporal or causal event chains), and cross-video complex reasoning (integrating commonsense and domain knowledge). Built from five domain-diverse video clusters (e.g., sports, life records), the benchmark challenges models to analyze and integrate spatiotemporal patterns from dynamic visual streams. Extensive evaluation of 10+ leading MLLMs (including GPT-4o, Gemini-2.0-flash, Qwen2.5-VL) under zero-shot or chain-of-thought prompting paradigms. Key findings reveal stark performance gaps: even top models, such as GPT-4o, achieve only 63.5% accuracy on causal reasoning tasks, compared to the 91.3% accuracy of human performance. Crucially, our analysis reveals fundamental bottlenecks inherent in current MLLMs architectures, notably deficient inter-video context retention and poor disambiguation of overlapping entities. CVBench establishes a rigorous framework for advancing pattern recognition methodologies in multi-video scenarios, providing architectural insights for next-generation models. The data and evaluation code are available at: https://github.com/Hokhim2/CVBench.