# Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards

arXiv: https://arxiv.org/abs/2510.20867 · HTML: https://mlsanity.com/paper/2510.20867/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix](https://mlsanity.com/paper/2505.13032/) (2025)
- [MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2506.04779/) (2025)
- [Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://mlsanity.com/paper/2503.02318/) (2025)
- [Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering](https://mlsanity.com/paper/2503.11197/) (2025)
- [Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model](https://mlsanity.com/paper/2501.07246/) (2025)
- [SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration](https://mlsanity.com/paper/2506.12723/) (2025)
- [Entire Space Counterfactual Learning for Reliable Content Recommendations](https://mlsanity.com/paper/2210.11039/) (2022)
- [A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions](https://mlsanity.com/paper/2112.04145/) (2021)
- [PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference](https://mlsanity.com/paper/2407.05010/) (2024)
- [An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning](https://mlsanity.com/paper/2106.00707/) (2021)
- [ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning](https://mlsanity.com/paper/2506.07459/) (2025)
- [Variational Supervised Contrastive Learning](https://mlsanity.com/paper/2506.07413/) (2025)
- [Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning](https://mlsanity.com/paper/2011.06752/) (2020)
- [ConvFormer: Revisiting Transformer for Sequential User Modeling](https://mlsanity.com/paper/2308.02925/) (2023)
- [CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration](https://mlsanity.com/paper/2105.03923/) (2021)

## Built on by (most cited first, 12 of 12)

- [Step-Audio-R1 Technical Report](https://mlsanity.com/paper/2511.15848/) (2025)
- [Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models](https://mlsanity.com/paper/2604.25591/) (2026)
- [Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning](https://mlsanity.com/paper/2607.20166/) (2026)
- [X3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment](https://mlsanity.com/paper/2607.21550/) (2026)
- [Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning](https://mlsanity.com/paper/2608.02831/) (2026)
- [When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning](https://mlsanity.com/paper/2603.02266/) (2026)
- [Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models](https://mlsanity.com/paper/2604.18187/) (2026)
- [SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learning](https://mlsanity.com/paper/2608.26432/) (2026)
- [Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition](https://mlsanity.com/paper/2606.07309/) (2026)
- [Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace](https://mlsanity.com/paper/2608.24958/) (2026)
- [Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language Models](https://mlsanity.com/paper/2609.28778/) (2026)
- [SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty](https://mlsanity.com/paper/2610.13081/) (2026)

## Abstract (arXiv)

The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inference, a phenomenon we term test-time inverse scaling, where longer reasoning chains yield progressively worse results. We demonstrate that this stems not from fundamental limitations of reasoning itself, but from inadequate training: models without proper guidance for the reasoning process produce hallucinatory, inconsistent reasoning that accumulates errors over longer chains. To address these challenges, we introduce CESAR (Consistent, Effective, and Scalable Audio Reasoners), shifting from outcome verification to rewarding the reasoning process. Our online reinforcement learning framework employs Group Relative Policy Optimization with a multi-faceted reward suite that incentivizes not only correctness and format but also consistency, structured analytical patterns, causal reasoning, domain-knowledge integration, and calibrated reasoning depth. CESAR resolves test-time inverse scaling, transforming reasoning from detriments into gains while revealing model-specific ``reasoning sweet spots", where performance peaks during test-time scaling. We achieve state-of-the-art results on MMAU Test-mini, substantially outperforming Gemini 2.5 Pro and GPT-4o Audio, and near-human-level performance on MMSU reasoning tasks. Through AI-as-judge evaluations and qualitative comparisons, we provide both quantitative and qualitative validation of our improved reasoning quality. Importantly, enhanced reasoning creates synergistic effects, simultaneously improving multimodal reasoning and perception capabilities. Overall, CESAR establishes a principled method for developing robust and scalable reasoning in Audio LLMs.