Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. Existing CoT compression methods often suffer from a critical loss of logical fidelity at high compression ratios, resulting in significant performance degradation. To achieve high-fidelity, fast reasoning, we propose a novel EXTreme-RAtio Chain-of-Thought Compression framework, termed Extra-CoT, which aggressively reduces the token budget while preserving answer accuracy. To generate reliable, high-fidelity supervision, we first train a dedicated semantically-preserved compressor on mathematical CoT data with fine-grained annotations. An LLM is then fine-tuned on these compressed pairs via a mixed-ratio supervised fine-tuning (SFT), teaching it to follow a spectrum of compression budgets and providing a stable initialization for reinforcement learning (RL). We further propose Constrained and Hierarchical Ratio Policy Optimization (CHRPO) to explicitly incentivize question-solving ability under lower budgets by a hierarchical reward. Experiments on three mathematical reasoning benchmarks show the superiority of Extra-CoT. For example, on MATH-500 using Qwen3-1.7B, Extra-CoT achieves over 73\% token reduction with an accuracy improvement of 0.6\%, significantly outperforming state-of-the-art (SOTA) methods. Our source codes have been released at https://github.com/Mwie1024/Extra-CoT.

翻译：思维链（Chain-of-Thought, CoT）推理有效增强了大型语言模型（LLMs）的推理能力，但同时也带来了显著的计算开销。现有CoT压缩方法在高压缩比下常出现关键性的逻辑保真度损失，导致性能严重下降。为实现高保真度的快速推理，我们提出了一种新颖的极端压缩比思维链框架，命名为Extra-CoT，该框架在保留答案准确性的同时，激进地减少token预算。为生成可靠的高保真度监督信号，我们首先在带有细粒度标注的数学CoT数据上，训练了一个专用的语义保持压缩器。随后，通过混合比例的监督微调（SFT）对LLM在这些压缩数据对上进行微调，使其能适应不同压缩预算，并为强化学习（RL）提供稳定的初始化。我们进一步提出了约束层级比率策略优化（CHRPO），通过层级奖励显式激励模型在较低预算下的解题能力。在三个数学推理基准上的实验表明，Extra-CoT具有优越性。例如，在MATH-500上使用Qwen3-1.7B时，Extra-CoT在实现超过73%的token缩减的同时，准确率提升了0.6%，显著优于当前最先进（SOTA）方法。我们的源代码已在https://github.com/Mwie1024/Extra-CoT 公开。