Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably evaluate long, implicitly structured reasoning traces, and (3) how to use such evaluation signals for reasoning optimization. To address these challenges, we provide a unified perspective. (1) We introduce the ME$^2$ principle to characterize reasoning quality along macro- and micro-level concerning efficiency and effectiveness. (2) Built on this principle, we model reasoning traces as directed acyclic graphs (DAGs) and develop a DAG-based pairwise evaluation method, capturing complex reasoning structures. (3) Based on this method, we construct the TRM-Preference dataset and train a Thinking Reward Model (TRM) to evaluate reasoning quality at scale. Experiments show that thinking rewards serve as an effective optimization signal. At test time, selecting better reasoning leads to better outcomes (up to 19.3% gain), and during RL training, thinking rewards enhance reasoning and performance (up to 3.9% gain) across diverse tasks.

翻译：大型推理模型（LRMs）日益依赖具有复杂内部结构的推理轨迹。然而，现有研究对三个基本问题缺乏统一解答：（1）如何定义高质量推理，（2）如何可靠地评估长且隐含结构的推理轨迹，以及（3）如何利用此类评估信号进行推理优化。为应对这些挑战，我们提供了一个统一视角。（1）我们引入ME$^2$原则，从宏观与微观层面、围绕效率与效能来表征推理质量。（2）基于此原则，我们将推理轨迹建模为有向无环图（DAGs），并开发了一种基于DAG的成对评估方法，以捕捉复杂的推理结构。（3）基于此方法，我们构建了TRM-Preference数据集，并训练了一个思维奖励模型（TRM）来大规模评估推理质量。实验表明，思维奖励可作为有效的优化信号。在测试阶段，选择更优的推理能带来更好的结果（最高提升19.3%）；在强化学习训练期间，思维奖励能提升多种任务的推理能力与性能（最高提升3.9%）。