English

SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models

Computation and Language 2025-09-23 v2 Multimedia Sound Audio and Speech Processing

Abstract

While large language models have demonstrated impressive reasoning abilities, their extension to the audio modality, particularly within large audio-language models (LALMs), remains underexplored. Addressing this gap requires a systematic approach that involves a capable base model, high-quality reasoning-oriented audio data, and effective training algorithms. In this work, we present a comprehensive solution for audio logical reasoning (ALR) tasks: we introduce SoundMind, a dataset of 6,446 audio-text annotated samples specifically curated to support complex reasoning. Building on this resource, we propose SoundMind-RL, a rule-based reinforcement learning (RL) algorithm designed to equip audio-language models with robust audio-text reasoning capabilities. By fine-tuning Qwen2.5-Omni-7B on the proposed SoundMind dataset using SoundMind-RL, we achieve strong and consistent improvements over state-of-the-art baselines on the SoundMind benchmark. This work highlights the benefit of combining high-quality, reasoning-focused datasets with specialized RL techniques, and contributes to advancing auditory intelligence in language models. The code and dataset introduced in this work are publicly available at https://github.com/xid32/SoundMind.

Keywords

Cite

@article{arxiv.2506.12935,
  title  = {SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models},
  author = {Xingjian Diao and Chunhui Zhang and Keyi Kong and Weiyi Wu and Chiyu Ma and Zhongyu Ouyang and Peijun Qing and Soroush Vosoughi and Jiang Gui},
  journal= {arXiv preprint arXiv:2506.12935},
  year   = {2025}
}

Comments

Accepted to EMNLP 2025 Main Conference (Oral Presentation)

R2 v1 2026-07-01T03:18:37.592Z