Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into textual tokens. Yet this capability also increases hallucinations, where the model generates content that is not supported by the input image or the question. To understand this failure mode, we identify \emph{reasoning drift}: during clue gathering, the model over-focuses on question-irrelevant entities, diluting focus on task-relevant cues and gradually decoupling the reasoning trace from visual grounding. As a consequence, many inference-time localization or intervention methods developed for non-reasoning models fail to pinpoint the true clues in reasoning settings. Motivated by these insights, we introduce ClueRecall, a metric for assessing visual clue retrieval, and present ClueTracer, a training-free, parameter-free, and architecture-agnostic plugin for hallucination suppression. ClueTracer starts from the question and traces how key clues propagate along the model's reasoning pathway (question $\rightarrow$ outputs $\rightarrow$ visual tokens), thereby localizing task-relevant patches while suppressing spurious attention to irrelevant regions. Remarkably, \textbf{without any additional training}, ClueTracer improves all \textbf{reasoning} architectures (including \texttt{R1-OneVision}, \texttt{Ocean-R1}, \texttt{MM-Eureka}, \emph{etc}.) by $\mathbf{1.21\times}$ on reasoning benchmarks. When transferred to \textbf{non-reasoning} settings, it yields a $\mathbf{1.14\times}$ gain.

翻译：大型多模态推理模型通过显式的长链推理解决具有挑战性的视觉问题：它们从图像中收集视觉线索，并将线索解码为文本标记。然而，这种能力也增加了幻觉的产生，即模型生成的内容缺乏输入图像或问题的支持。为了理解这种失效模式，我们识别了“推理漂移”现象：在收集线索的过程中，模型过度关注与问题无关的实体，从而稀释了对任务相关线索的注意力，并逐渐使推理轨迹与视觉基础解耦。因此，许多为非推理模型开发的推理时定位或干预方法无法在推理场景中精确定位真实线索。基于这些洞见，我们引入了ClueRecall，一个用于评估视觉线索检索的指标，并提出了ClueTracer，一个无需训练、无需额外参数且与架构无关的幻觉抑制插件。ClueTracer从问题出发，追踪关键线索如何沿着模型的推理路径（问题→输出→视觉标记）传播，从而定位任务相关的图像块，同时抑制对无关区域的虚假注意力。值得注意的是，在无需任何额外训练的情况下，ClueTracer将所有推理架构（包括R1-OneVision、Ocean-R1、MM-Eureka等）在推理基准上的性能提升了1.21倍。当迁移至非推理场景时，它也能带来1.14倍的性能增益。