FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations 事件

FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations arXiv:2507.07644v4 Announce Type: replace Abstract: We introduce FloorplanQA, a diagnostic benchmark for evaluating spatial reasoning in large language models (LLMs). FloorplanQA is grounded in structured representations of indoor scenes, such as (e.g., kitchens, living rooms, bedrooms, bathrooms, and others), encoded symbolically in JSON or XML layouts. The benchmark covers core spatial tasks, including dis