# Soft Spatial Reasoning

The work proposes Soft Spatial Reasoning, a post-training framework in which a large vision-language model forms a continuous soft state at each chain-of-thought step by mixing token embeddings instead of committing to a single token, with an AdaptSoft controller that adapts the degree of softness from the current hidden state and predictive uncertainty and is trained by a gradient-alignment objective; across OmniSpatial, SpatiaLab, and MindCube it reaches higher weighted-average accuracy than same-backbone hard-thinking and fixed-soft chain-of-thought baselines and the compared existing models.

The work proposes Soft Spatial Reasoning, a post-training framework in which a large vision-language model forms a continuous soft state at each chain-of-thought step by mixing token embeddings instead of committing to a single token, with an AdaptSoft controller that adapts the degree of softness from the current hidden state and predictive uncertainty and is trained by a gradient-alignment objective; across OmniSpatial, SpatiaLab, and MindCube it reaches higher weighted-average accuracy than same-backbone hard-thinking and fixed-soft chain-of-thought baselines and the compared existing models.