AI RESEARCH
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
arXiv CS.CV
•
ArXi:2602.13294v3 Announce Type: replace Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynamics remains challenging. Most existing benchmarks rely on recognition-style protocols such as Visual Question Answering (VQA) and Violation of Expectation (VoE), which can often be answered without committing to an explicit, testable physical hypothesis. We propose VisPhyWorld, an execution-based framework that evaluates physical reasoning by requiring models to generate executable simulator code from visual observations.