# A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding

arXiv: https://arxiv.org/abs/2603.14733 · HTML: https://mlsanity.com/paper/2603.14733/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (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)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [MLVU: Benchmarking Multi-task Long Video Understanding](https://mlsanity.com/paper/2406.04264/) (2024)
- [VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding](https://mlsanity.com/paper/2403.11481/) (2024)
- [WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection](https://mlsanity.com/paper/2101.01456/) (2021)
- [SpatialVID: A Large-Scale Video Dataset with Spatial Annotations](https://mlsanity.com/paper/2509.09676/) (2025)
- [VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT](https://mlsanity.com/paper/2504.04471/) (2025)
- [Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs](https://mlsanity.com/paper/2510.13795/) (2025)
- [FIVR: Fine-grained Incident Video Retrieval](https://mlsanity.com/paper/1809.04094/) (2018)
- [CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning](https://mlsanity.com/paper/2508.19542/) (2025)
- [Open-World Object Counting in Videos](https://mlsanity.com/paper/2506.15368/) (2025)
- [MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs](https://mlsanity.com/paper/2511.07250/) (2025)
- [ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos](https://mlsanity.com/paper/2311.01620/) (2023)
- [ANIM-400K: A Large-Scale Dataset for Automated End-To-End Dubbing of Video](https://mlsanity.com/paper/2401.05314/) (2024)
- [CI-VID: A Coherent Interleaved Text-Video Dataset](https://mlsanity.com/paper/2507.01938/) (2025)
- [ConViS-Bench: Estimating Video Similarity Through Semantic Concepts](https://mlsanity.com/paper/2509.19245/) (2025)
- [Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment](https://mlsanity.com/paper/2506.22385/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos remains limited. Existing approaches typically concatenate multiple videos into a single input and perform direct inference, which introduces training-inference mismatch, information loss from frame compression, and a lack of explicit cross-video coordination. Meanwhile, current multi-video benchmarks primarily emphasize event-level comparison, leaving identity-level matching, fine-grained discrimination, and structured multi-step reasoning underexplored. To address these gaps, we introduce MVX-Bench, a Multi-Video Cross-Dimension Benchmark that reformulates 11 classical computer vision tasks into a unified multi-video question-answering framework, comprising 1,442 questions over 4,255 videos from diverse real-world datasets. We further propose SAMA, a Skill-Augmented Agentic Framework for Multi-Video Understanding, which integrates visual tools, task-specific skills, and a conflict-aware verification mechanism to enable iterative and structured reasoning. Experimental results show that SAMA outperforms strong open-source baselines and GPT on MVX-Bench, and ablations validate the effectiveness of skill design and conflict resolution.