Score: 2

AudioToolAgent: An Agentic Framework for Audio-Language Models

Published: October 3, 2025 | arXiv ID: 2510.02995v1

By: Gijs Wijngaard, Elia Formisano, Michel Dumontier

Potential Business Impact:

Lets computers understand and answer questions about sounds.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Large Audio-Language Models (LALMs) perform well on audio understanding tasks but lack multi-step reasoning and tool-calling found in recent Large Language Models (LLMs). This paper presents AudioToolAgent, a framework that coordinates audio-language models as tools via a central LLM agent that accesses tool adapters for audio question answering and speech-to-text. The agent selects tools, asks follow-up questions, and compares outputs for verification. Experiments with MMAU, MMAR, and MMAU-Pro show state-of-the-art accuracy: up to 74.10% on MMAU, 68.80% on MMAR, and 57.96% on MMAU-Pro. Monte Carlo sampling for shapley values across 374 configurations identifies effective agent-tool combinations. The modular design allows integration of new tools and eliminates the use of data and training costs. Code and reproduction materials are available at: github.com/GLJS/AudioToolAgent

Repos / Data Links

Page Count
7 pages

Category
Computer Science:
Sound