Haocun Ye

The work proposes a "visual resolvability" design rule requiring that correct answers depend on visual evidence while the task stays learnable, and tests it on counterfactual coordinate scenes with standard GRPO and correctness-and-format rewards on Qwen2.5-VL-7B: on held-out 20-point scenes denser than any seen in training, discovery accuracy rises from 0.425 to 0.875; replacing test images with gray canvases drops accuracy to zero, while training on gray canvases at matched step 30 across four seeds yields essentially none of the gain, indicating the gain comes from training images; adding a caption that answers the training question, with the same images, reward and budget, cuts the gain by nearly two thirds.

The work proposes a "visual resolvability" design rule requiring that correct answers depend on visual evidence while the task stays learnable, and tests it on counterfactual coordinate scenes with standard GRPO and correctness-and-format rewards on Qwen2.5-VL-7B: on held-out 20-point scenes denser than any seen in training, discovery accuracy rises from 0.425 to 0.875; replacing test images with gray canvases drops accuracy to zero, while training on gray canvases at matched step 30 across four seeds yields essentially none of the gain, indicating the gain comes from training images; adding a caption that answers the training question, with the same images, reward and budget, cuts the gain by nearly two thirds.