让大模型学会根据任务难易自动调节思考深度。
Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning
- 用自适应强化学习动态调整推理深度。
- 在多模态任务上比基线提升显著，尤其复杂任务表现更好。
- 适合需要智能决策的多模态应用开发者参考。
近期的Omni模型实现了统一的多模态感知与生成。然而，现有系统仍存在推理行为僵化的问题，要么对简单问题过度思考，要么在必要时无法推理。为此，我们提出Omni-AutoThink，一种自适应推理框架，可根据任务难度动态调整模型的推理深度。该框架包含两个阶段：(1) 自适应监督微调（Adaptive SFT），利用大规模带推理增强的数据赋予Omni模型基本推理能力；(2) 自适应强化学习（Adaptive GRPO），基于任务复杂度和奖励反馈优化推理行为。我们还构建了一个涵盖文本、文本-音频、文本-视觉及文本-音频-视觉模态的综合性自适应推理基准，提供训练与评估数据集。实验结果表明，所提框架在自适应推理性能上显著优于先前基线。所有基准数据与代码将公开发布。
原文摘要 · Abstract (English)
Recent advances in Omni models have enabled unified multimodal perception and generation. However, most existing systems still exhibit rigid reasoning behaviors, either overthinking simple problems or failing to reason when necessary. To address this limitation, we propose Omni-AutoThink, a novel adaptive reasoning framework that dynamically adjusts the model's reasoning depth according to task difficulty. Our framework comprises two stages: (1) an Adaptive Supervised Fine-Tuning (Adaptive SFT) stage, which endows the Omni model with fundamental reasoning capability using large-scale reasoning-augmented data, and (2) an Adaptive Reinforcement Learning (Adaptive GRPO) stage, which optimizes reasoning behaviors based on task complexity and reward feedback. We further construct a comprehensive adaptive reasoning benchmark that spans text-only, text-audio, text-visual, and text-audio-visual modalities, providing both training and evaluation splits for multimodal reasoning assessment. Experimental results demonstrate that our proposed framework significantly improves adaptive reasoning performance compared to previous baselines. All benchmark data and code will be publicly released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。