# AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation

arXiv: https://arxiv.org/abs/2505.22053 · HTML: https://mlsanity.com/paper/2505.22053/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- First posted on arXiv 28 May 2025.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Built on by (most cited first, 6 of 6)

- [Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing](https://mlsanity.com/paper/2604.10708/) (2026)
- [AutoMV: An Automatic Multi-Agent System for Music Video Generation](https://mlsanity.com/paper/2512.12196/) (2025)
- [EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation](https://mlsanity.com/paper/2512.24731/) (2025)
- [Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games](https://mlsanity.com/paper/2604.11741/) (2026)
- [VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation](https://mlsanity.com/paper/2606.26534/) (2026)
- [OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue](https://mlsanity.com/paper/2609.21465/) (2026)

## Abstract (arXiv)

Multimodality-to-Multiaudio (MM2MA) generation faces significant challenges in synthesizing diverse and contextually aligned audio types (e.g., sound effects, speech, music, and songs) from multimodal inputs (e.g., video, text, images), owing to the scarcity of high-quality paired datasets and the lack of robust multi-task learning frameworks. Recently, multi-agent system shows great potential in tackling the above issues. However, directly applying it to MM2MA task presents three critical challenges: (1) inadequate fine-grained understanding of multimodal inputs (especially for video), (2) the inability of single models to handle diverse audio events, and (3) the absence of self-correction mechanisms for reliable outputs. To this end, we propose AudioGenie, a novel training-free multi-agent system featuring a dual-layer architecture with a generation team and a supervisor team. For the generation team, a fine-grained task decomposition and an adaptive Mixture-of-Experts (MoE) collaborative entity are designed for detailed comprehensive multimodal understanding and dynamic model selection, and a trial-and-error iterative refinement module is designed for self-correction. The supervisor team ensures temporal-spatial consistency and verifies outputs through feedback loops. Moreover, we build MA-Bench, the first benchmark for MM2MA tasks, comprising 198 annotated videos with multi-type audios. Experiments demonstrate that our AudioGenie achieves state-of-the-art (SOTA) or comparable performance across 9 metrics in 8 tasks. User study further validates the effectiveness of our method in terms of quality, accuracy, alignment, and aesthetic. The project website with audio samples can be found at https://audiogenie.github.io/.