mlsanityData to 14 Oct 2026

Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning

arXiv 2510.11454 ↗First posted 13 Oct 2025cs.SD cs.AIcited by 3

On the map: LLM reasoning → Audio-language model reasoning

also in 1 more
Abstract (arXiv)

Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solely on end-to-end reasoning, limiting interpretability and accuracy for tasks that require structured knowledge or specialized signal analysis. In this work, we present Audio-Maestro -- a tool-augmented audio reasoning framework that enables audio-language models to autonomously call external tools and integrate their timestamped outputs into the reasoning process. This design allows the model to analyze, transform, and interpret audio signals through specialized tools rather than relying solely on end-to-end inference. Experiments show that Audio-Maestro consistently improves general audio reasoning performance: Gemini-2.5-flash's average accuracy on MMAU-Test rises from 67.4% to 72.1%, DeSTA-2.5 from 58.3% to 62.8%, and GPT-4o from 60.8% to 63.9%. To our knowledge, Audio-Maestro is the first framework to integrate structured tool output into the large audio language model reasoning process.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 28 references that are in the map. First posted on arXiv 13 Oct 2025.

Builds on

21 of 28 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning11 Aug
  2. 2025Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering14 Mar
  3. 2025Mellow: a small audio language model for reasoning11 Mar
  4. 2025Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models4 Mar
  5. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark24 Oct

Other references · 16

  1. 2024GPT-4o System Cardcited by 4,588
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  5. 2023Large Language Modelscited by 780
  6. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  7. 2021AST: Audio Spectrogram Transformercited by 643
  8. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 506
  9. 2023emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representationcited by 205
  10. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 197
  11. 2025Step-Audio 2 Technical Reportcited by 105
  12. 2025Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaborationcited by 41
4 more
  1. 2024DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignmentcited by 33
  2. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  3. 2022Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimationcited by 23
  4. 2025TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modelingcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoningcited by 3
  2. 2026Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoningcited by 3
  3. 2026SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
  2. 2026Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models
  3. 2026A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models
  4. 2026AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning
  5. 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
  6. 2025Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
  7. 2026Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
  8. 2024GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities