Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

TL;DR

This paper introduces Extra-CoT, a novel framework for compressing Chain-of-Thought reasoning in large language models, significantly reducing tokens while maintaining or improving accuracy, especially in mathematical reasoning tasks.

Contribution

The paper proposes a new compression method with a dedicated compressor, mixed-ratio fine-tuning, and hierarchical policy optimization to enhance reasoning efficiency without sacrificing fidelity.

Findings

Achieves over 73% token reduction with improved accuracy on MATH-500.

Outperforms state-of-the-art methods in mathematical reasoning benchmarks.

Demonstrates effective high-fidelity compression for large language models.

Abstract

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.