mlsanityData to 7 Oct 2026

Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model

arXiv 2501.07246 ↗First posted 13 Jan 2025cs.SD cs.CL cs.MMcited by 60

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

Abstract (arXiv)

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in tasks involving audio perception and understanding, such as speech recognition and audio captioning. However, their reasoning capabilities - critical for solving complex real-world problems - remain underexplored. In this work, we conduct the first exploration into integrating Chain-of-Thought (CoT) reasoning into LALMs to enhance their reasoning ability across auditory modalities. We evaluate representative CoT methods, analyzing their performance in both information extraction and reasoning tasks across sound, music, and speech domains. Our findings reveal that CoT methods significantly improve performance on easy and medium tasks but encounter challenges with hard tasks, where reasoning chains can confuse the model rather than improve accuracy. Additionally, we identify a positive correlation between reasoning path length and accuracy, demonstrating the potential of scaling inference for advanced instruction-following and reasoning. This study not only highlights the promise of CoT in enhancing LALM reasoning capabilities but also identifies key limitations and provides actionable directions for future research.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 36 of its 41 references that are in the map. First posted on arXiv 13 Jan 2025.

Builds on

36 of 41 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark24 Oct
  2. 2024GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities17 Jun

Other references · 34

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  5. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  6. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
  7. 2024Qwen2-Audio Technical Reportcited by 543
  8. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 492
  9. 2024AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehensioncited by 215
  10. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  11. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  12. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 183
22 more
  1. 2023On decoder-only architecture for speech-to-text and large language model integrationcited by 144
  2. 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 140
  3. 2023Prompting Large Language Models with Speech Recognition Abilitiescited by 139
  4. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 125
  5. 2024AudioBench: A Universal Benchmark for Audio Large Language Modelscited by 124
  6. 2024M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thoughtcited by 120
  7. 2024OmniBench: Towards The Future of Universal Omni-Language Modelscited by 100
  8. 2023Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speechcited by 99
  9. 2023Joint Audio and Speech Understandingcited by 99
  10. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 86
  11. 2023Connecting Speech Encoder and Large Language Model for ASRcited by 79
  12. 2024A Survey on Speech Large Language Models for Understandingcited by 71
  13. 2024Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognitioncited by 61
  14. 2023Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognitioncited by 48
  15. 2023Sparks of Large Audio Models: A Survey and Outlookcited by 41
  16. 2024Towards audio language modeling -- an overviewcited by 40
  17. 2023The Role of Chain-of-Thought in Complex Vision-Language Reasoning Taskcited by 32
  18. 2024VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Musiccited by 30
  19. 2024CTC-Assisted LLM-Based Contextual ASRcited by 18
  20. 2024SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMscited by 15
  21. 2024Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasetscited by 13
  22. 2024DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioningcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 36; 2026: 24.

60 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  3. 2025MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mixcited by 113
  4. 2025Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Modelscited by 94
  5. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  6. 2025Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answeringcited by 64
  7. 2025DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignmentcited by 47
  8. 2025SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learningcited by 31
  9. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 29
  10. 2025Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learningcited by 19
  11. 2025WavReward: Spoken Dialogue Models With Generalist Reward Evaluatorscited by 15
  12. 2025VoiceAgentBench: Are Voice Assistants ready for agentic tasks?cited by 15
38 more
  1. 2025SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Modelscited by 14
  2. 2025SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Modelscited by 14
  3. 2025Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Studycited by 11
  4. 2025Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generationcited by 11
  5. 2025Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewardscited by 11
  6. 2026MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Modelscited by 11
  7. 2025Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoningcited by 8
  8. 2025From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Datacited by 7
  9. 2026The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agentscited by 6
  10. 2025Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generationcited by 5
  11. 2025AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Taskscited by 5
  12. 2025Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understandingcited by 5
  13. 2025Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Modelscited by 5
  14. 2026LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoningcited by 5
  15. 2026Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Modelscited by 4
  16. 2026Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoningcited by 3
  17. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  18. 2025Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillationcited by 2
  19. 2025Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbonescited by 2
  20. 2026Spatial Audio Question Answering and Reasoning on Dynamic Source Movementscited by 2
  21. 2026Learning When to Think While Listening in Large Audio-Language Modelscited by 2
  22. 2025WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizationscited by 1
  23. 2025Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answeringcited by 1
  24. 2025SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Modelscited by 1
  25. 2025Investigating Faithfulness in Large Audio Language Modelscited by 1
  26. 2025CMDAR: A Chinese Multi-scene Dynamic Audio Reasoning Benchmark with Diverse Challengescited by 1
  27. 2026Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Modelscited by 1
  28. 2026Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Modelscited by 1
  29. 2026EChO-Agent: Evidence Chain Orchestration Agent for Audio Reasoningcited by 1
  30. 2026Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoningcited by 1
  31. 2026Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoningcited by 1
  32. 2026Enhancing Audio Reasoning via Semantic Summary Predictioncited by 1
  33. 2025MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translationcited by 0
  34. 2025MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixingcited by 0
  35. 2025Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-Thoughtcited by 0
  36. 2025Thinking While Listening: Simple Test Time Scaling For Audio Classificationcited by 0
  37. 2025Evaluating Hallucinations in Audio-Visual Multimodal LLMs with Spoken Queries under Diverse Acoustic Conditionscited by 0
  38. 2026When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoningcited by 0

50 most cited of 60 All 60 (JSON)

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. 2025Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models
  3. 2026Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
  4. 2025SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
  5. 2026AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning
  6. 2026Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models
  7. 2025Can Speech LLMs Think while Listening?
  8. 2025Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning