REVIEW 24 cited by
Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
read the original abstract
Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio modality has largely been overlooked in these developments. Thus, we conduct a series of RL explorations in audio understanding and reasoning, specifically focusing on the audio question answering (AQA) task. We leverage the group relative policy optimization (GRPO) algorithm to Qwen2-Audio-7B-Instruct, and our experiments demonstrated state-of-the-art performance on the MMAU Test-mini benchmark, achieving an accuracy rate of 64.5%. The main findings in this technical report are as follows: 1) The GRPO algorithm can be effectively applied to large audio language models (LALMs), even when the model has only 8.2B parameters; 2) With only 38k post-training samples, RL significantly outperforms supervised fine-tuning (SFT), indicating that RL-based approaches can be effective without large datasets; 3) The explicit reasoning process has not shown significant benefits for AQA tasks, and how to efficiently utilize deep thinking remains an open question for further research; 4) LALMs still lag far behind humans auditory-language reasoning, suggesting that the RL-based approaches warrant further exploration. Our project is available at https://github.com/xiaomi-research/r1-aqa and https://huggingface.co/mispeech/r1-aqa.
Forward citations
Cited by 24 Pith papers
-
Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
ToxiAlert-Bench dataset and dual-head neural network detect toxic speech by distinguishing textual versus paralinguistic sources, reporting 21.1% Macro-F1 and 13% accuracy gains over baselines.
-
Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
Omni-Persona benchmark with 18 tasks shows open-source models have audio-visual grounding gaps, RLVR narrows them but leads to conservative outputs, and scale or recall alone fail as diagnostics.
-
VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing
VERITAS is a multi-agent system for verifiable hypothesis testing on multimodal clinical MRI datasets that achieves 81.4% verdict accuracy with frontier models and introduces an epistemic evidence labeling framework.
-
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
Audio Flamingo 3 introduces an open large audio-language model achieving new state-of-the-art results on over 20 audio understanding and reasoning benchmarks using a unified encoder and curriculum training on open data.
-
Weak-to-Strong On-Policy Distillation
A strong LLM is improved by distilling from the logit difference of two weaker models instead of from a stronger teacher.
-
Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning
A self-play game with a known 'odd listener' converts unlabeled audio contrast pairs into a verifiable reward, improving fine-grained audio reasoning on TREA, MMAU, and MMAR.
-
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
AV-Flamingo is an open audio-visual language model that outperforms similarly sized open models on many long-video understanding benchmarks, using a new 7M-question dataset and timestamped reasoning.
-
LaSR: Context-Aware Speech Recognition via Latent Reasoning
LaSR improves context-aware terminology recognition in speech LLMs by aligning latent CoT supervision on acoustic regions and introducing latent reasoning periods, shown on a new academic corpus to outperform standard...
-
Learning When to Think While Listening in Large Audio-Language Models
A wait-think-answer controller for LALMs is trained via SFT followed by six-reward DAPO, raising row-weighted accuracy from 67.6% to 70.3% and cutting post-endpoint thinking length by 14% on synthetic spoken QA while ...
-
Why Your Tokenizer Fails in Information Fusion: A Timing-Aware Pre-Quantization Fusion for Video-Enhanced Audio Tokenization
A timing-aware pre-quantization fusion approach integrates visual cues into audio tokenizers along the temporal axis, maintaining reconstruction quality while outperforming audio-only and prior multimodal baselines on...
-
VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing
A four-phase multi-agent co-scientist tests natural-language hypotheses on cardiac and glioma MRI and labels outcomes Supported, Refuted, Underpowered, or Invalid with an executable evidence trail.
-
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
LongVT adds native video-cropping tool calling to LMMs for interleaved multimodal chain-of-tool-thought reasoning on long videos and releases VideoSIAH data for training and evaluation.
-
Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
MPS proposes a dual-brain architecture separating formulation reasoning from articulation to achieve real-time CoT in SLMs with accuracy comparable to full pre-computation but much lower latency.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
-
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
X3-OPD improves audio-grounded reasoning by training the audio student on its own rollouts with token-level teacher feedback, using a three-tier paired text-audio corpus.
-
Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
A hybrid-reward progressive RL curriculum enables high-quality chain-of-thought to emerge in audio language models without prior supervised CoT training, yielding SOTA results on MMAR, MMAU, and MMSU benchmarks.
-
TinyMU: A Compact Audio-Language Model for Music Understanding
TinyMU is a 229M-parameter compact music understanding model that achieves 82% of state-of-the-art large audio-language model performance on the MuChoMusic benchmark while being 35 times smaller.
-
AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
Test-time reinforcement learning against self-generated majority-vote pseudo-labels improves audio question answering accuracy on MMAU, MMAR, and MMSU.
-
Group Relative Policy Optimization for Speech Recognition
Applying GRPO with rule-based rewards to LLM-based ASR improves WER by up to 18.4% relative and reduces hallucination errors on unseen acoustic conditions.
-
FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations
FSA-GRPO applies reinforcement learning with a few-shot-aware reward to auditory LLMs, improving few-shot performance on children's ASR, speech translation, and audio tasks when trained only on adult data.
-
VISA: A Visual Information Strengthened Audio-Reasoning System for the Interspeech 2026 ARC Agent Track
VISA ranks 2nd in the Interspeech 2026 ARC Agent Track by adding multi-modal feature extraction, consistency-checked model voting, and rubric-aligned routing to large audio language models, reaching 66.23% Rubrics sco...
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
-
A Survey of Audio Reasoning in Multimodal Foundation Models
A survey that provides a unified formulation of audio reasoning and reviews advances across Audio-to-Text, Audio-to-Speech, Audio-Visual, and Agentic paradigms while discussing challenges and future directions.
-
Empowering Multimodal LLMs with External Tools: A Comprehensive Survey
A survey paper maps how external tools are used to augment multimodal large language models across data, tasks, evaluation, and future directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.