Structured Reasoning Agentic Framework for Interpretable Critical View of Safety Assessment
ReasonCVS is proposed, a structured reasoning agentic framework empowered by Vision-Language Models (VLMs) that decomposes CVS assessment into explicit, fine-grained anatomical verification and introduces a Rationale-Aware Reasoning Agent, powered by a Large Language Model (LLM) fine-tuned via rationale distillation.