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

• URL: http://arxiv.org/abs/2510.20867v1
• Date: Thu, 23 Oct 2025 06:18:10 GMT
• Title: Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
• Authors: Jiajun Fan, Roger Ren, Jingyuan Li, Rahul Pandey, Prashanth Gurunath Shivakumar, Ivan Bulyko, Ankur Gandhe, Ge Liu, Yile Gu,
• Abstract summary: We develop a principled method for developing robust and scalable reasoning in Audio Large Language Models.<n>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.
• Score: 24.40159537923851
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution [79.98699884805636]
  Reasoning Execution by Multiple Listeners (REMUL) is a multi-party reinforcement learning approach.<n>REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful.<n>Speakers are rewarded for producing reasoning that is clear to listeners.
  arXiv  Detail & Related papers  (2026-02-18T02:55:55Z)
• Does Your Reasoning Model Implicitly Know When to Stop Thinking? [45.954548163594204]
  We show that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms.<n>Motivated by this, we introduce SAGE, a novel sampling paradigm that unleashes this efficient reasoning potential.
  arXiv  Detail & Related papers  (2026-02-09T07:38:22Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models [50.84995206660551]
  We introduce Conditional advANtage estimatiON (CANON) to amplify the impact of a target metric without presuming its direction.<n>CANON based on entropy consistently outperforms prior methods on both math reasoning and high-complexity logic tasks.
  arXiv  Detail & Related papers  (2025-09-28T16:33:07Z)
• Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning [41.255832127671205]
  We propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of large audio language models (LALMs)<n>Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task dynamically.<n> Experimental results demonstrate that our Audio-Thinker model outperforms existing reasoning-oriented LALMs across various benchmark tasks.
  arXiv  Detail & Related papers  (2025-08-11T14:41:10Z)
• Lost at the Beginning of Reasoning [85.17612793300238]
  We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.
  arXiv  Detail & Related papers  (2025-06-27T09:53:57Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models [63.98194996746229]
  Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization.<n>However, reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations.<n>We propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification.
  arXiv  Detail & Related papers  (2025-05-30T14:23:32Z)
• Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model [26.20569269005708]
  Large Audio-Language Models (LALMs) have demonstrated remarkable performance in tasks involving audio perception and understanding.<n>However, their reasoning capabilities - critical for solving complex real-world problems - remain underexplored.<n>We conduct the first exploration into integrating Chain-of-Thought (CoT) reasoning into LALMs to enhance their reasoning ability across auditory modalities.
  arXiv  Detail & Related papers  (2025-01-13T11:54:40Z)
• CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistency [11.144164626192904]
  Chain-based methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs)<n>This paper proposes a non-chain-based reasoning framework for simultaneous consideration of causal significance and consistency.
  arXiv  Detail & Related papers  (2024-09-20T08:28:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.