When More Is Less: A Systematic Analysis of Spatial and Commonsense Information for Visual Spatial Reasoning
This work addresses the challenge of reliable multimodal reasoning for AI systems, providing practical guidance, though it is incremental as it analyzes existing methods rather than introducing new ones.
The paper tackled the problem of visual spatial reasoning (VSR) in vision-language models by analyzing how injecting additional information like spatial cues and commonsense knowledge affects performance, finding that more information often degrades accuracy and targeted cues yield better results.
Visual spatial reasoning (VSR) remains challenging for modern vision-language models (VLMs), despite advances in multimodal architectures. A common strategy is to inject additional information at inference time, such as explicit spatial cues, external commonsense knowledge, or chain-of-thought (CoT) reasoning instructions. However, it remains unclear when such information genuinely improves reasoning and when it introduces noise. In this paper, we conduct a hypothesis-driven analysis of information injection for VSR across three representative VLMs and two public benchmarks. We examine (i) the type and number of spatial contexts, (ii) the amount and relevance of injected commonsense knowledge, and (iii) the interaction between spatial grounding and CoT prompting. Our results reveal a consistent pattern: more information does not necessarily yield better reasoning. Targeted single spatial cues outperform multi-context aggregation, excessive or weakly relevant commonsense knowledge degrades performance, and CoT prompting improves accuracy only when spatial grounding is sufficiently precise. These findings highlight the importance of selective, task-aligned information injection and provide practical guidance for designing reliable multimodal reasoning pipelines.