S2R: Selective-Stability Repair in Frozen Vision-Language Models

Vision–language models can be unstable when an answer should stay the same and insensitive when its visual support is weakened. We call the desired behavior *selective stability*: agreement across answer-preserving text and image changes, coupled with reduced confidence when proposed visual evidence is attenuated. **S2R** turns this criterion into a test-time repair signal. It reads answers at several points along the base reasoning trajectory and fits a temporary, hard-sparse edit of visual-token states in an otherwise frozen model. Hyperparameters and gate thresholds are selected on separate calibration data. On Qwen3-VL-8B-Thinking, S2R raises macro-average accuracy from 72.4% to 75.5%, while S2R-Full reaches 75.7%. The improvement transfers to two other frozen 8B backbones, and ablations show that preserving views, the directional evidence constraint, and localized support contribute complementary gains.