Large language models have shown strong reasoning capabilities through chain-structured methods such as Chain-of-Thought. Recent studies optimize thought structures by generating parallel or tree-like structures, switching between long and short reasoning modes, or aligning reasoning steps with task performance. However, these approaches mainly rely on previously generated logical directions of the chains, which ignore the unexplored regions of the solution space. Such a phenomenon is defined as blind spots, which limit the diversity and effectiveness of the reasoning process. To this end, we propose the ``Thought Space Explorer'' (TSE), a framework for navigating and expanding thought structures to overcome blind spots in LLM reasoning. Our TSE first identifies key nodes with high impact, then generates new nodes by integrating information from multiple chains. Finally, it extends new branches through connection strategies. We conduct a series of experiments on math and QA benchmarks. Compared with existing baseline methods, TSE improves the accuracy of both the final answer and intermediate reasoning steps, while maintaining a better effectiveness-efficiency trade-off for practical deployment.

翻译：大语言模型通过如思维链等链式结构方法展现出强大的推理能力。近期研究通过生成并行或树状结构、在长短推理模式间切换，或使推理步骤与任务性能对齐来优化思维结构。然而，这些方法主要依赖于先前生成的链式逻辑方向，忽略了解决方案空间中未探索的区域。这种现象被定义为盲点，限制了推理过程的多样性与有效性。为此，我们提出“思维空间探索器”（TSE），一个用于导航与扩展思维结构以克服大语言模型推理中盲点的框架。我们的TSE首先识别具有高影响力的关键节点，然后通过整合来自多条链的信息生成新节点，最后通过连接策略扩展新分支。我们在数学与问答基准测试上进行了一系列实验。与现有基线方法相比，TSE在保持实际部署中更优的效果-效率权衡的同时，提升了最终答案与中间推理步骤的准确性。