混合思维树：结合快慢思考实现多跳视觉推理
Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
AI总结：
针对多跳视觉推理中LLM规划搜索难以兼顾效率与准确率的问题，受人类快慢思考双认知系统启发，提出融合一站式推理与思维树的分层规划搜索算法，经改造的PTR、CLEVER数据集验证，在性能与效率上均更优。
摘要：
当前出现了一种颇具前景的趋势：利用大语言模型（LLM）为视觉推理等复杂推理任务生成类代码规划。这种被称为基于LLM的规划范式为问题求解提供了灵活性，也赋予了更强的可解释性。但现有研究大多局限于简单问题的基础场景，这类问题仅需几步推理就能直接得出答案，针对更具挑战性的多跳视觉推理任务的规划研究仍有待深入。具体而言，在多跳推理场景下，规划搜索的准确率与复杂度之间的权衡问题十分突出。现有主流算法要么采用快速的一站式生成来解决效率问题，要么使用复杂的迭代生成方法提升准确率，二者都无法兼顾效率与性能需求。受人类大脑双认知系统（快思考与慢思考过程）的启发，我们提出了一种分层规划搜索算法，该算法融合了一站式推理（快思考）和思维树（Tree-of-thought，慢思考）。我们的方法在保证性能的同时，大幅减少了推理步骤。此外，我们改造了PTR和CLEVER数据集，构建了一个系统评估框架，用于评测基于LLM的规划搜索算法在不同难度推理任务下的性能和效率。大量实验证明，我们提出的算法在性能和效率方面均具备优势。相关数据集和代码即将发布。
英文摘要：
There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and endows better interpretability. However, current research is mostly limited to basic scenarios of simple questions that can be straightforward answered in a few inference steps. Planning for the more challenging multi-hop visual reasoning tasks remains under-explored. Specifically, under multi-hop reasoning situations, the trade-off between accuracy and the complexity of plan-searching becomes prominent. The prevailing algorithms either address the efficiency issue by employing the fast one-stop generation or adopt a complex iterative generation method to improve accuracy. Both fail to balance the need for efficiency and performance. Drawing inspiration from the dual system of cognition in the human brain, the fast and the slow think processes, we propose a hierarchical plan-searching algorithm that integrates the one-stop reasoning (fast) and the Tree-of-thought (slow). Our approach succeeds in performance while significantly saving inference steps. Moreover, we repurpose the PTR and the CLEVER datasets, developing a systematic framework for evaluating the performance and efficiency of LLMs-based plan-search algorithms under reasoning tasks at different levels of difficulty. Extensive experiments demonstrate the superiority of our proposed algorithm in terms of performance and efficiency. The dataset and code will be release soon.
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。
