Large reasoning models trained with reinforcement learning and verifiable rewards (RLVR) achieve strong performance on complex reasoning tasks, yet often overthink, generating redundant reasoning without performance gains. Existing trajectory-level length penalties often fail to effectively shorten reasoning length and degrade accuracy, as they uniformly treat all reasoning steps and lack fine-grained signals to distinguish redundancy from necessity. Meanwhile, process-supervised methods are typically resource-intensive and suffer from inaccurate credit assignment. To address these issues, we propose ATTNPO, a low-overhead process-supervised RL framework that leverages the model's intrinsic attention signals for step-level credit assignment. We first identify a set of special attention heads that naturally focus on essential steps while suppressing redundant ones. By leveraging the attention scores of these heads, We then employ two sub-strategies to mitigate overthinking by discouraging redundant steps while preserving accuracy by reducing penalties on essential steps. Experimental results show that ATTNPO substantially reduces reasoning length while significantly improving performance across 9 benchmarks.

翻译：通过强化学习和可验证奖励训练的大型推理模型在复杂推理任务上表现强劲，但常出现“过度思考”现象，即生成冗余推理而性能未见提升。现有轨迹级长度惩罚方法通常无法有效缩短推理长度且会降低准确性，因为它们统一处理所有推理步骤，缺乏区分冗余与必要性的细粒度信号。同时，过程监督方法通常资源消耗大且存在信用分配不准确的问题。为解决这些问题，我们提出ATTPNO——一种低开销的过程监督强化学习框架，利用模型内在的注意力信号进行步骤级信用分配。我们首先识别出一组特殊的注意力头，它们天生关注必要步骤而抑制冗余步骤。通过利用这些注意力头的分数，我们采用两种子策略：通过抑制冗余步骤缓解过度思考，同时通过减少对必要步骤的惩罚来保持准确性。实验结果表明，ATTPNO在9个基准测试中显著缩短了推理长度，同时大幅提升了性能。