CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs

• URL: http://arxiv.org/abs/2606.19927v1
• Date: Thu, 18 Jun 2026 08:28:26 GMT
• Title: CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs
• Abstract summary: We propose CARE, a competence-aware reward shaping framework for adaptive reasoning length optimization in multimodal reasoning.<n> CARE maintains a smoothed competence estimate via an exponential moving average of pass rates, and uses it to route training into progressive stages.<n>Experiments on multiple video reasoning and general video understanding benchmarks demonstrate that CARE consistently improves reasoning accuracy, stabilizes reinforcement learning, and significantly enhances token efficiency.
• Score: 50.189987475377656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In multimodal video reasoning, reinforcement learning-based methods typically rely on simplistic and inflexible reasoning-length control strategies that fail to adapt to the model's evolving competence. This mismatch may suppress necessary exploration at early stages, while encouraging redundant reasoning and inefficient decoding once the model becomes more competent. In this paper, we propose CARE, a competence-aware reward shaping framework for adaptive reasoning length optimization in multimodal reasoning. Specifically, CARE maintains a smoothed competence estimate via an exponential moving average of pass rates, and uses it to route training into progressive stages that shift the reward preference from exploration-oriented long-form reasoning to efficiency-oriented concise reasoning. To avoid conflating verbosity with intrinsic task complexity, CARE further normalizes reasoning effort with batch-level statistics, and introduces a posterior amplifier to strengthen reward signals for unexpectedly strong performance on historically difficult samples. The proposed mechanism is seamlessly integrated into the GRPO training pipeline and incurs no additional inference-time overhead. Extensive experiments on multiple video reasoning and general video understanding benchmarks demonstrate that CARE consistently improves reasoning accuracy, stabilizes reinforcement learning, and significantly enhances token efficiency. Moreover, CARE exhibits a characteristic inverted-U trajectory of reasoning length during training, and yields shorter yet more informative reasoning traces at convergence, indicating effective adaptive allocation of reasoning budget. We provide the source code for our proposed CARE framework and experiments at https://github.com/1Pansy/Video-CARE.

Related papers

• Constraint-Rectified Training for Efficient Chain-of-Thought [60.52883907721588]
  Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs)<n>While longer reasoning traces can improve answer quality and unlock abilities such as self-correction, they also incur high inference costs and often introduce redundant steps, known as overthinking.<n>Recent research seeks to develop efficient reasoning strategies that balance reasoning length and accuracy.
  arXiv  Detail & Related papers  (2026-02-13T02:13:45Z)
• 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)
• InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning [50.185363583880225]
  InftyThink+ is an end-to-end reinforcement learning framework for large reasoning models.<n>We show that InftyThink+ improves accuracy by 21% and outperforms conventional long chain-of-thought reinforcement learning.
  arXiv  Detail & Related papers  (2026-02-06T18:59:27Z)
• BARD: budget-aware reasoning distillation [25.725960386304646]
  Long Chain-of-Thought (CoT) distillation effectively transfers reasoning capability to smaller language models.<n>We propose bftextBudget-Aware Reasoning Distillation (BARD), a novel framework that simultaneously distills reasoning capability and enables fine-grained control over the reasoning length.
  arXiv  Detail & Related papers  (2025-11-03T11:30:18Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards [24.40159537923851]
  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.
  arXiv  Detail & Related papers  (2025-10-23T06:18:10Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control [18.273777938294327]
  Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts.<n>We introduce AALC, a lightweight, accuracy-aware length reward integrated into reinforcement learning.<n>We show that our approach reduces response length by over 50% while maintaining or even improving the original accuracy.
  arXiv  Detail & Related papers  (2025-06-25T06:29:18Z)
• Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning [95.44766931218896]
  Multi-modal large language models (MLLMs) still lag behind text-based reasoning.<n>We introduce Perception-Reasoning Decoupling, which modularizes the MLLM's reasoning component and makes it easily replaceable.<n>We propose a novel reinforcement learning algorithm called Visual Perception Optimization (VPO) to align the MLLM's perceptual output with the final reasoning task.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)

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.