Abstract
Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a tool-guided inference framework for the DataCV 2026 Challenge (Tasks I and II) that addresses this failure mode without any model training. An off-the-shelf vision-language model is given access to a small set of generic image manipulation tools: line drawing, region cropping, side-by-side comparison, and channel isolation, together with an illusion-type-routing system prompt that prescribes which tools to invoke for each perceptual question category. Critically, every tool call produces a new, immutable image resource appended to a persistent registry, so the model can reference and compose any prior annotated view throughout its reasoning chain. Rather than hard-coding illusion-specific modules, this generic-tool-plus-routing design yields strong cross-structural generalization: performance remained consistent from the validation set to a test set containing structurally unfamiliar illusion variants (e.g., Mach Bands rotated from vertical to horizontal stacking). We further report three empirical observations that we believe warrant additional investigation: (i) a strong positive-detection bias likely rooted in imbalanced illusion training data, (ii) a striking dissociation between pixel-accurate spatial reasoning and logical inference over self-generated annotations, and (iii) pronounced sensitivity to image compression artifacts that compounds false positives.
Abstract (translated)
视觉语言模型（VLMs）在面对经典光学幻觉时表现出系统性偏见：无论图像是否经过反事实修改，它们几乎总是将幻觉预测为“真实”的。我们提出了一种用于DataCV 2026挑战赛（任务I和II）的工具引导推理框架，该框架无需任何模型训练即可解决此失效模式。我们赋予一个现成的视觉语言模型访问一组通用图像处理工具的权限：线条绘制、区域裁剪、并排比较和通道隔离，同时配备一个幻觉类型路由系统提示，该系统提示规定了针对每类感知问题应调用哪些工具。关键在于，每次工具调用都会生成一个新的不可变图像资源，并将其追加到持久注册表中，从而使模型能够在整个推理链中引用和组合任何先前的注释视图。与硬编码幻觉特定模块不同，这种通用工具加路由的设计实现了强大的跨结构泛化：在验证集和包含结构不熟悉的幻觉变体（例如马赫带效应从垂直堆叠旋转为水平堆叠）的测试集上，性能保持稳定。我们还报告了三个我们认为值得进一步研究的实证观察结果：（i）一种强烈的正向检测偏见，可能源于不平衡的幻觉训练数据；（ii）像素精确的空间推理与对自生成注释的逻辑推理之间存在显著分离；（iii）对图像压缩伪影的明显敏感度，这加剧了假阳性结果。
URL
https://arxiv.org/abs/2603.29428
