AStar: 通过自动化结构化思维提升多模态推理
AStar: Boosting Multimodal Reasoning with Automated Structured Thinking
AI总结：
AStar通过自动化结构化思维提升多模态推理效率，实现更高准确率和更强迁移能力。
摘要：
多模态大语言模型在各种领域中表现出色，但在复杂的视觉推理任务上却面临挑战。为了增强其推理能力，当前方法通常依赖于显式搜索或训练后技术。然而，基于搜索的方法由于需要探索庞大的解决方案空间而效率低下，而训练后的方法则需要大量数据、计算资源，且往往表现出训练不稳定。为了解决这些挑战，我们提出了AStar，一种无需训练的自动化结构化思维范式，用于多模态推理。具体来说，我们引入了新的“思维卡片”，这是一个轻量级的高层次推理模式库，抽象自先前样本。对于每个测试问题，AStar会自适应地检索最优的思维卡片，并无缝地将这些外部显式指导与模型内部的隐式推理能力相结合。与之前的方法相比，AStar消除了计算成本高昂的显式搜索，避免了额外的复杂训练后过程，从而实现更高效的推理方法。广泛的实验表明，我们的框架在MathVerse上实现了53.9%的准确率（超过GPT-4o的50.2%），在MathVision上实现了32.7%的准确率（超过GPT-4o的30.4%）。进一步分析显示，我们的方法具有显著的迁移能力：从数学推理生成的思维卡片也可以应用于其他推理任务，甚至有助于一般的视觉感知和理解。AStar作为一种即插即用的测试时间推理方法，与其他训练后技术兼容，为现有的多模态推理方法提供了重要的补充。
英文摘要：
Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques. However, search-based methods suffer from computational inefficiency due to extensive solution space exploration, while post-training methods demand substantial data, computational resources, and often exhibit training instability. To address these challenges, we propose \textbf{AStar}, a training-free, \textbf{A}utomatic \textbf{S}tructured \textbf{t}hinking paradigm for multimod\textbf{a}l \textbf{r}easoning. Specifically, we introduce novel ``thought cards'', a lightweight library of high-level reasoning patterns abstracted from prior samples. For each test problem, AStar adaptively retrieves the optimal thought cards and seamlessly integrates these external explicit guidelines with the model's internal implicit reasoning capabilities. Compared to previous methods, AStar eliminates computationally expensive explicit search and avoids additional complex post-training processes, enabling a more efficient reasoning approach. Extensive experiments demonstrate that our framework achieves 53.9\% accuracy on MathVerse (surpassing GPT-4o's 50.2\%) and 32.7\% on MathVision (outperforming GPT-4o's 30.4\%). Further analysis reveals the remarkable transferability of our method: thought cards generated from mathematical reasoning can also be applied to other reasoning tasks, even benefiting general visual perception and understanding. AStar serves as a plug-and-play test-time inference method, compatible with other post-training techniques, providing an important complement to existing multimodal reasoning approaches.
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。
