Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like ``overthinking'' simple problems and ``underthinking'' complex ones. While existing methods that use supervised fine-tuning~(SFT) or reinforcement learning~(RL) with token-length rewards can improve efficiency, they often do so at the cost of accuracy. This paper introduces \textbf{DeepCompress}, a novel framework that simultaneously enhances both the accuracy and efficiency of LRMs. We challenge the prevailing approach of consistently favoring shorter reasoning paths, showing that longer responses can contain a broader range of correct solutions for difficult problems. DeepCompress employs an adaptive length reward mechanism that dynamically classifies problems as ``Simple'' or ``Hard'' in real-time based on the model's evolving capability. It encourages shorter, more efficient reasoning for ``Simple'' problems while promoting longer, more exploratory thought chains for ``Hard'' problems. This dual-reward strategy enables the model to autonomously adjust its Chain-of-Thought (CoT) length, compressing reasoning for well-mastered problems and extending it for those it finds challenging. Experimental results on challenging mathematical benchmarks show that DeepCompress consistently outperforms baseline methods, achieving superior accuracy while significantly improving token efficiency.

翻译：大型推理模型（LRMs）已展现出卓越的能力，但存在认知效率低下的问题，例如对简单问题“过度思考”和对复杂问题“思考不足”。现有方法通过监督微调（SFT）或基于令牌长度的强化学习（RL）奖励可提升效率，但往往以牺牲准确性为代价。本文提出 \textbf{DeepCompress}，一种新颖的框架，旨在同时提升LRMs的准确性与效率。我们挑战了当前普遍倾向于更短推理路径的做法，证明对于困难问题，更长的响应可能包含更广泛的正确解决方案。DeepCompress采用自适应长度奖励机制，根据模型动态演化的能力，实时将问题分类为“简单”或“困难”。它鼓励对“简单”问题采用更短、更高效的推理，同时对“困难”问题促进更长、更具探索性的思维链。这种双重奖励策略使模型能够自主调整其思维链（CoT）长度，压缩对已掌握问题的推理，并扩展对其感到挑战性问题的推理。在具有挑战性的数学基准测试上的实验结果表明，DeepCompress持续优于基线方法，在显著提升令牌效率的同时实现了更优的准确性。