Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation
For vision-language models, this work addresses the trade-off between fine-grained reasoning accuracy and inference efficiency by eliminating the need for external tool invocations during inference.
The paper proposes Imagine-OPD, an on-policy self-distillation framework that internalizes visual reasoning benefits of explicit image cropping into an imagination process, achieving best average performance on vision-centric benchmarks while significantly reducing inference overhead compared to explicit cropping methods.
''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoning over crops, models can access local evidence that is difficult to recover from a single global image. However, this benefit comes with redundant tool invocations and longer inference traces. Moreover, when such behaviors are learned mainly from outcome reward, the resulting intermediate crops or visual cues can be noisy or fail to faithfully capture task-relevant visual evidence. In this work, we ask whether the reasoning benefits of ''Thinking with Images'' can be internalized through Thinking with Imagination: an internal process that decides where to look and imagines what visual cues closer inspection would reveal without actually invoking tools. We propose Imagine-OPD, an on-policy self-distillation framework in which a teacher plays the role of a ''Thinking with Images'' reasoner during training: it receives privileged zoomed evidence views derived from annotated regions, and supervises the model's own imagination reasoning trajectories. Imagine-OPD does not require an external teacher or high-quality imagination demonstrations. Experiments on vision-centric benchmarks show that Imagine-OPD achieves the best average performance among compared models while significantly reducing inference overhead compared with ''Thinking with Images'' methods.