SmartSwitch：通过促进更深层的思维探索克服思考不足以推进大语言模型推理
SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration
AI总结：
针对大语言模型长思维链推理中存在的思考不足问题，提出即插即用的SmartSwitch框架，通过监控思维切换、回溯高潜力思维并插入深化提示引导深度探索，显著提升了不同规模大模型在数学推理基准上的性能。
摘要：
长思维链（LongCoT）能力是大语言模型近期在复杂推理任务中取得突破的核心。然而，伴随而来的“思考不足”问题——模型频繁切换思维却未充分探索，呈现出浅层推理的特征——限制了其性能与token效率。为解决该问题，我们提出一种简单却有效的推理策略：SmartSwitch推理框架。该框架可作为即插即用方案轻松集成到任意大语言模型中，持续监控模型的推理过程以检测思考不足问题，并引导模型对有潜力但被忽略的思维进行更深层探索。具体而言，感知模块识别思维切换点，并利用现成的过程奖励模型（PRM）评估前序思维的潜力。若发现高潜力思维被过早放弃，干预模块会中断正在进行的推理，回溯到切换前的节点，并插入“深化提示”以鼓励模型沿着该有潜力的路径进一步探索。在具有挑战性的数学推理基准上开展的大量实验表明，我们的方法显著提升了不同规模的各类大语言模型的性能。
英文摘要：
The long chain-of-thought (LongCoT) capability is central to the recent breakthroughs achieved by large language models in complex reasoning tasks. However, the accompanying issue of ''underthinking'', where models exhibit shallow reasoning by frequently switching thoughts without sufficient exploration, limits both performance and token efficiency. To address this problem, we propose a simple yet effective reasoning strategy: the SmartSwitch inference framework. This framework can be easily integrated into any large language model as a plug-and-play solution, continuously monitoring the model's reasoning process to detect underthinking and guide it toward deeper exploration of promising but overlooked thoughts. Specifically, the perception module identifies points where thoughts switch and evaluates the potential of the preceding thought using an off-the-shelf process reward model (PRM). If a high-potential thought is found to be prematurely abandoned, the intervention module interrupts the ongoing inference, backtracks to the point before the switch, and inserts a "deepening prompt" to encourage further exploration along that promising path. Extensive experiments on challenging mathematical reasoning benchmarks demonstrate that our method significantly enhances the performance of various large language models of different sizes.
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。
