Parse Before You Execute: Efficient Spatial Reasoning with Executable Primitives

The paper introduces PEPS, a training‑free framework that improves spatial reasoning in Vision‑Language Models by parsing queries into a compact set of executable requirements before execution. PEPS uses a typed FESM schema (Frame, Entity, State, Metric) to commit queries, then selectively grounds primitives via fixed geometric APIs and verifies sufficiency, allowing early termination or targeted repair. Experiments on spatial reasoning benchmarks show that PEPS boosts accuracy while reducing refinement rounds, API cost, and latency compared to existing tool‑integrated baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• llms
• agents
• multimodal
• benchmarks