Recent advances in large language models (LLMs) have demonstrated their potential in handling complex reasoning tasks, which are usually achieved by constructing a thought chain to guide the model to solve the problem with multi-step thinking. However, existing methods often remain confined to previously explored solution spaces and thus overlook the critical blind spot within LLMs' cognitive range. To address these issues, we design the Thought Space Explorer (TSE), a novel framework to expand and optimize thought structures to guide LLMs to explore their blind spots of thinking. By generating new reasoning steps and branches based on the original thought structure with various designed strategies, TSE broadens the thought space and alleviates the impact of blind spots for LLM reasoning. Experimental results on multiple levels of reasoning tasks demonstrate the efficacy of TSE. We also conduct extensive analysis to understand how structured and expansive thought can contribute to unleashing the potential of LLM reasoning capabilities.

翻译：近年来，大型语言模型（LLMs）在处理复杂推理任务方面展现出巨大潜力，这通常通过构建思维链来引导模型进行多步思考以解决问题。然而，现有方法往往局限于先前探索过的解空间，因而忽视了LLMs认知范围内的关键盲区。为解决这些问题，我们设计了思维空间探索者（TSE），这是一个用于扩展和优化思维结构以引导LLMs探索其思维盲区的新颖框架。通过基于原始思维结构、采用多种设计策略生成新的推理步骤和分支，TSE拓宽了思维空间并减轻了思维盲区对LLM推理的影响。在多个层级的推理任务上的实验结果表明了TSE的有效性。我们还进行了广泛分析，以理解结构化且具扩展性的思维如何有助于释放LLM推理能力的潜力。