# XGC-AVis: Towards Audio-Visual Content Understanding with a Multi-Agent Collaborative System

arXiv: https://arxiv.org/abs/2509.23251 · HTML: https://mlsanity.com/paper/2509.23251/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2025.

## Built on by (most cited first, 2 of 2)

- [Active Perception Agent for Omnimodal Audio-Video Understanding](https://mlsanity.com/paper/2512.23646/) (2025)
- [OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering](https://mlsanity.com/paper/2602.03707/) (2026)

## Abstract (arXiv)

In this paper, we propose XGC-AVis, a multi-agent framework that enhances the audio-video temporal alignment capabilities of multimodal large models (MLLMs) and improves the efficiency of retrieving key video segments through 4 stages: perception, planning, execution, and reflection. We further introduce XGC-AVQuiz, the first benchmark aimed at comprehensively assessing MLLMs' understanding capabilities in both real-world and AI-generated scenarios. XGC-AVQuiz consists of 2,685 question-answer pairs across 20 tasks, with two key innovations: 1) AIGC Scenario Expansion: The benchmark includes 2,232 videos, comprising 1,102 professionally generated content (PGC), 753 user-generated content (UGC), and 377 AI-generated content (AIGC). These videos cover 10 major domains and 53 fine-grained categories. 2) Quality Perception Dimension: Beyond conventional tasks such as recognition, localization, and reasoning, we introduce a novel quality perception dimension. This requires MLLMs to integrate low-level sensory capabilities with high-level semantic understanding to assess audio-visual quality, synchronization, and coherence. Experimental results on XGC-AVQuiz demonstrate that current MLLMs struggle with quality perception and temporal alignment tasks. XGC-AVis improves these capabilities without requiring additional training, as validated on two benchmarks.