mlsanityData to 14 Oct 2026

Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models

arXiv 2503.02318 ↗First posted 4 Mar 2025cs.SD cs.AI cs.CLcited by 95

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

Abstract (arXiv)

Recent advancements in multimodal reasoning have largely overlooked the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning in audio tasks. We meticulously curated a large-scale and diverse multi-task audio dataset with simple annotations. Then, we leverage closed-source models to conduct secondary labeling, QA generation, along with structured COT process. These datasets together form a high-quality reasoning dataset with 1.2 million reasoning-rich samples, which we name CoTA. Following inference scaling principles, we train Audio-Reasoner on CoTA, enabling it to achieve great logical capabilities in audio reasoning. Experiments show state-of-the-art performance across key benchmarks, including MMAU-mini (+25.42%), AIR-Bench chat/foundation(+14.57%/+10.13%), and MELD (+8.01%). Our findings stress the core of structured CoT training in advancing audio reasoning.

Key facts. Cited by 95 papers in the map (data through 14 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 57 of its 71 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

57 of 71 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model13 Jan
  2. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark24 Oct
  3. 2024Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming29 Aug
  4. 2024GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities17 Jun

Other references · 53

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  10. 2025s1: Simple test-time scalingcited by 1,341
  11. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  12. 2024Qwen2.5-Coder Technical Reportcited by 1,203
38 more
  1. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  2. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  3. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  4. 2018MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversationscited by 643
  5. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  6. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  7. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  8. 2024Qwen2-Audio Technical Reportcited by 560
  9. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 529
  10. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 506
  11. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 454
  12. 2019Clotho: An Audio Captioning Datasetcited by 358
  13. 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 355
  14. 2023PandaGPT: One Model To Instruction-Follow Them Allcited by 334
  15. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 288
  16. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 263
  17. 2024From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Stepcited by 235
  18. 2024AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehensioncited by 220
  19. 2023Listen, Think, and Understandcited by 209
  20. 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interactioncited by 197
  21. 2020Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPOcited by 186
  22. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 186
  23. 2024Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognitioncited by 153
  24. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutionscited by 144
  25. 2024Improve Vision Language Model Chain-of-thought Reasoningcited by 136
  26. 2024Token-level Direct Preference Optimizationcited by 135
  27. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 127
  28. 2024Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilitiescited by 109
  29. 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 103
  30. 2023Joint Audio and Speech Understandingcited by 100
  31. 2023Mustango: Toward Controllable Text-to-Music Generationcited by 100
  32. 2023BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writingcited by 79
  33. 2024o1-Coder: an o1 Replication for Codingcited by 78
  34. 2023Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioningcited by 77
  35. 2024Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Modelscited by 65
  36. 2024VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selectioncited by 65
  37. 2024EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmarkcited by 40
  38. 2024VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Toolcited by 35

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 47; 2026: 48.

95 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 182
  3. 2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 118
  4. 2025MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mixcited by 117
  5. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  6. 2025Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answeringcited by 65
  7. 2025SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learningcited by 34
  8. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 30
  9. 2025STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Modelscited by 26
  10. 2025Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Modelscited by 21
  11. 2026Large Language Model Reasoning Failurescited by 21
  12. 2025Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learningcited by 19
38 more
  1. 2025Multimodal Large Language Models Meet Multimodal Emotion Recognition and Reasoning: A Surveycited by 19
  2. 2025SHANKS: Simultaneous Hearing and Thinking for Spoken Language Modelscited by 19
  3. 2025MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Modelscited by 17
  4. 2025WavReward: Spoken Dialogue Models With Generalist Reward Evaluatorscited by 15
  5. 2025SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearingcited by 15
  6. 2025SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Modelscited by 15
  7. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 14
  8. 2025SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Modelscited by 14
  9. 2025Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problemscited by 12
  10. 2025Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Studycited by 12
  11. 2025Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agentscited by 12
  12. 2025Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewardscited by 12
  13. 2026MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Modelscited by 12
  14. 2025UALM: Unified Audio Language Model for Understanding, Generation and Reasoningcited by 10
  15. 2025Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Modelscited by 9
  16. 2025From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Datacited by 7
  17. 2026LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoningcited by 7
  18. 2026Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learningcited by 6
  19. 2026AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answeringcited by 6
  20. 2026The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agentscited by 6
  21. 2025AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Taskscited by 5
  22. 2025Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understandingcited by 5
  23. 2025Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Modelscited by 5
  24. 2025Robustness assessment of large audio language models in multiple-choice evaluationcited by 5
  25. 2026Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understandingcited by 5
  26. 2026OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimizationcited by 5
  27. 2026Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulationcited by 5
  28. 2026Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Modelscited by 4
  29. 2026Audio Interaction Modelcited by 4
  30. 2025LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Modelcited by 3
  31. 2025Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoningcited by 3
  32. 2026Research on World Models Is Not Merely Injecting World Knowledge into Specific Taskscited by 3
  33. 2026AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoningcited by 3
  34. 2026Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoningcited by 3
  35. 2026X3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignmentcited by 3
  36. 2026Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoningcited by 3
  37. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  38. 2025WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizationscited by 2

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models
  2. 2025Mellow: a small audio language model for reasoning
  3. 2025Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
  4. 2026Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
  5. 2026A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models
  6. 2025SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
  7. 2026ReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrieval
  8. 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities