mlsanityData to 7 Oct 2026

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

arXiv 2506.12935 ↗First posted 15 Jun 2025cs.CL cs.MM cs.SDcited by 14

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

Abstract (arXiv)

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.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 25 of its 47 references that are in the map. First posted on arXiv 15 Jun 2025.

Builds on

25 of 47 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Qwen2.5-Omni Technical Report26 Mar
  2. 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities6 Mar
  3. 2025Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models4 Mar
  4. 2025Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model13 Jan

Other references · 21

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  2. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  3. 2024OpenAI o1 System Cardcited by 1,220
  4. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  5. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  6. 2024Qwen2-Audio Technical Reportcited by 543
  7. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 446
  8. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learningcited by 260
  9. 2025REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalizationcited by 233
  10. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutionscited by 142
  11. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 125
  12. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 109
9 more
  1. 2025Baichuan-Omni-1.5 Technical Reportcited by 107
  2. 2025MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesiscited by 39
  3. 2024InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoningcited by 36
  4. 2023Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentationcited by 30
  5. 2022Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translationcited by 20
  6. 2025Learning Musical Representations for Music Performance Question Answeringcited by 17
  7. 2024Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Modelscited by 15
  8. 2022Text-To-Speech Data Augmentation for Low Resource Speech Recognitioncited by 6
  9. 2025Music Audio-Visual Question Answering Requires Specialized Multimodal Designscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 5.

14 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  2. 2025CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimizationcited by 24
  3. 2025UALM: Unified Audio Language Model for Understanding, Generation and Reasoningcited by 10
  4. 2025FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adaptercited by 7
  5. 2025Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understandingcited by 5
  6. 2025Enhancing Speech Large Language Models through Reinforced Behavior Alignmentcited by 1
  7. 2025Rebellion: Noise-Robust Reasoning Training for Audio Reasoning Modelscited by 1
  8. 2026Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessmentcited by 1
  9. 2026PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmarkcited by 1
  10. 2025Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkerscited by 0
  11. 2025A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecturecited by 0
  12. 2026DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusioncited by 0
2 more
  1. 2026Disentangling Reasoning in Large Audio-Language Models for Ambiguous Emotion Predictioncited by 0
  2. 2026SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning
  2. 2026AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning
  3. 2026Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models
  4. 2026Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
  5. 2025Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
  6. 2025SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning
  7. 2025Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
  8. 2026X3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment