mlsanityData to 14 Oct 2026

Step-Audio-R1 Technical Report

arXiv 2511.15848 ↗First posted 19 Nov 2025cs.AI cs.CL cs.SDcited by 36

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

Abstract (arXiv)

Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon persists in audio language models: they consistently perform better with minimal or no reasoning, raising a fundamental question - can audio intelligence truly benefit from deliberate thinking? We introduce Step-Audio-R1, the first audio reasoning model that successfully unlocks reasoning capabilities in the audio domain. Through our proposed Modality-Grounded Reasoning Distillation (MGRD) framework, Step-Audio-R1 learns to generate audio-relevant reasoning chains that genuinely ground themselves in acoustic features rather than hallucinating disconnected deliberations. Our model exhibits strong audio reasoning capabilities, surpassing Gemini 2.5 Pro and achieving performance comparable to the state-of-the-art Gemini 3 Pro across comprehensive audio understanding and reasoning benchmarks spanning speech, environmental sounds, and music. These results demonstrate that reasoning is a transferable capability across modalities when appropriately anchored, transforming extended deliberation from a liability into a powerful asset for audio intelligence. By establishing the first successful audio reasoning model, Step-Audio-R1 opens new pathways toward building truly multimodal reasoning systems that think deeply across all sensory modalities.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 23 of its 29 references that are in the map. First posted on arXiv 19 Nov 2025.

Builds on

23 of 29 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards23 Oct
  2. 2025Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models10 Oct
  3. 2025Chronological Thinking in Full-Duplex Spoken Dialogue Language Models2 Oct
  4. 2025Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning11 Aug
  5. 2025MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark5 Jun
  6. 2025Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering14 Mar
  7. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark24 Oct

Other references · 16

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  8. 2023Let's Verify Step by Stepcited by 3,789
  9. 2024Qwen2 Technical Reportcited by 2,120
  10. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  11. 2024Qwen2-Audio Technical Reportcited by 560
  12. 2025Qwen3-Omni Technical Reportcited by 497
4 more
  1. 2025Step-Audio 2 Technical Reportcited by 105
  2. 2025Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decodingcited by 55
  3. 2025Skywork-R1V3 Technical Reportcited by 16
  4. 2025Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problemscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 36.

36 papers.

Sort:

By area:

  1. 2026Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Musiccited by 19
  2. 2026Covo-Audio Technical Reportcited by 7
  3. 2026WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Modelscited by 6
  4. 2026The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agentscited by 6
  5. 2026ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Modelscited by 6
  6. 2026Towards Robust Speech Deepfake Detection via Human-Inspired Reasoningcited by 4
  7. 2026From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Benchcited by 4
  8. 2026Research on World Models Is Not Merely Injecting World Knowledge into Specific Taskscited by 3
  9. 2026The Latent Bridge: A Continuous Slow-Fast Channel for Real-Time Game Agentscited by 3
  10. 2026X3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignmentcited by 3
  11. 2026Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoningcited by 3
  12. 2026Speech LLMs are Contextual Reasoning Transcriberscited by 2
24 more
  1. 2026TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosiscited by 2
  2. 2026Learning When to Think While Listening in Large Audio-Language Modelscited by 2
  3. 2026Liberating LLM Capabilities in Full-Duplex Speech Modelscited by 2
  4. 2026Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videoscited by 2
  5. 2026FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generationcited by 2
  6. 2026Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialoguecited by 2
  7. 2026When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoningcited by 1
  8. 2026LaSR: Context-Aware Speech Recognition via Latent Reasoningcited by 1
  9. 2026RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmarkcited by 1
  10. 2026Never Stop Thinking: Continuous-Time Language Agentscited by 1
  11. 2026AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Modelscited by 1
  12. 2026BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoningcited by 0
  13. 2026Attention-guided Evidence Grounding for Spoken Question Answeringcited by 0
  14. 2026Multi-Source Evidence Fusion for Audio Question Answeringcited by 0
  15. 2026VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Modelscited by 0
  16. 2026Speech-based Psychological Crisis Assessment using LLMscited by 0
  17. 2026Noisy-Channel Minimum Bayes Risk Decodingcited by 0
  18. 2026Large Audio Language Models for Spoofing-Aware Speaker Verificationcited by 0
  19. 2026DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialectscited by 0
  20. 2026Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterizationcited by 0
  21. 2026HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Groundingcited by 0
  22. 2026Transcribe, Then Reason: Two-Pass Decomposition for Multimodal Reviewcited by 0
  23. 2026Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agentscited by 0
  24. 2026SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficultycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
  2. 2025SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models
  3. 2025Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
  4. 2025Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model
  5. 2026AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning
  6. 2025Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding
  7. 2026Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
  8. 2026Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models