原子步骤分解能否增强多模态大模型的自结构化推理？
Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?
AI总结：
针对多模态数学推理任务，提出由最小语义原子步骤构成的自结构化思维链范式及AtomThink框架，显著提升模型准确率、数据利用率与推理效率。
摘要：
在本文中，我们通过将“慢思考”能力融入多模态大语言模型（MLLMs），来解决多模态数学推理这一具有挑战性的任务。我们的核心思想是，不同层级的推理能力可以动态结合，以应对不同复杂度的问题。为此，我们提出了自结构化思维链（Self-structured Chain of Thought, SCoT）范式，该范式由最小语义原子步骤构成。与依赖结构化模板或自由形式范式的现有方法不同，我们的方法不仅能为各类复杂任务生成认知性思维链结构，还能缓解过度思考现象。为将结构化推理能力引入视觉理解模型，我们进一步设计了全新的AtomThink框架，该框架包含四个关键模块：（i）用于生成高质量多模态推理路径的数据引擎；（ii）基于序列化推理数据的监督微调流程；（iii）策略引导的多轮推理方法；（iv）用于评估单步利用率的原子能力指标。我们开展了大量实验，结果表明所提出的AtomThink显著提升了基线多模态大语言模型的性能，在MathVista和MathVerse数据集上实现了超过10%的平均准确率提升。与当前最优的结构化思维链方法相比，我们的方法不仅取得了更高的准确率，还将数据利用率提升了5倍，推理效率提高了85.3%。我们的代码现已在https://github.com/Quinn777/AtomThink 上公开。
英文摘要：
In this paper, we address the challenging task of multimodal mathematical reasoning by incorporating the ability of "slow thinking" into multimodal large language models (MLLMs). Our core idea is that different levels of reasoning abilities can be combined dynamically to tackle questions with different complexity. To this end, we propose a paradigm of Self-structured Chain of Thought (SCoT), which is composed of minimal semantic atomic steps. Different from existing methods that rely on structured templates or free-form paradigms, our method can not only generate cognitive CoT structures for various complex tasks but also mitigates the phenomenon of overthinking. To introduce structured reasoning capabilities into visual understanding models, we further design a novel AtomThink framework with four key modules, including (i) a data engine to generate high-quality multimodal reasoning paths; (ii) a supervised fine-tuning process with serialized inference data; (iii) a policy-guided multi-turn inference method; and (iv) an atomic capability metric to evaluate the single step utilization rate. We conduct extensive experiments to show that the proposed AtomThink significantly improves the performance of baseline MLLMs, achieving more than 10\% average accuracy gains on MathVista and MathVerse. Compared to state-of-the-art structured CoT approaches, our method not only achieves higher accuracy but also improves data utilization by 5 times and boosts inference efficiency by 85.3\%. Our code is now public available in https://github.com/Quinn777/AtomThink.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
