Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL). In this paper, we systematically investigate the mechanics of efficient reasoning for LLMs. For comprehensive evaluation, we advocate for more fine-grained metrics, including length distribution conditioned on correctness and performance across a wide spectrum of token budgets ranging from 2k to 32k. First, we reveal that the training process follows a two-stage paradigm: length adaptation and reasoning refinement. After that, we conduct extensive experiments (about 0.2 million GPU hours) in a unified protocol, deconstructing training prompts and rollouts, reward shaping, and optimization strategies. In particular, a key finding is to train on relatively easier prompts, ensuring the density of positive reward signals and thus avoiding the length collapse. Meanwhile, the learned length bias can be generalized across domains. We distill all findings into valuable insights and practical guidelines, and further validate them across the Qwen3 series, ranging from 0.6B to 30B, demonstrating the robustness and generalization.

翻译：大型语言模型（LLMs）持续受益于规模化的思维链（CoT）推理，但也承受着沉重的计算开销。为解决这一问题，高效推理旨在激励简短而准确的思维轨迹，通常通过强化学习（RL）的奖励塑形来实现。本文系统性地研究了LLMs高效推理的机制。为进行全面评估，我们提倡采用更细粒度的度量标准，包括基于正确性的长度分布以及在2k至32k广泛令牌预算范围内的性能表现。首先，我们揭示了训练过程遵循两阶段范式：长度适应与推理精炼。随后，我们在统一协议下进行了大量实验（约20万GPU小时），解构了训练提示与推演、奖励塑形以及优化策略。特别地，一个关键发现是在相对简单的提示上进行训练，以确保正向奖励信号的密度，从而避免长度崩溃。同时，习得的长度偏差能够跨领域泛化。我们将所有发现提炼为有价值的见解与实践指南，并进一步在Qwen3系列（0.6B至30B）上进行了验证，证明了其鲁棒性与泛化能力。