AI 中文总结
研究针对视觉语言模型物理推理评估不足问题，引入回顾性物理过程推理范式，提出RetroHolmes基准，通过它分析模型，发现失败模式，还展示综合分析实例，验证其诊断价值，凸显物理基础中间表示对物理推理的重要性。
AI 中文摘要
人类可以从稀疏观察中推断隐藏的物理过程，但当前视觉语言模型的评估协议未能评估这种物理推理是否被真正捕捉。为填补这一空白，我们引入回顾性物理过程推理，这是一种在明确物理约束下从结果反向推理的新评估范式。在此范式基础上，我们提出RetroHolmes，首个用于回顾性物理过程推理的真实世界基准，包含以物体为中心的图像对及跨不同物理转变的可达性标签和因果步骤序列注释。利用RetroHolmes，我们分析了当前先进的视觉语言模型，发现了系统的失败模式，如可达性评估中的判断偏差和信念凌驾于物理证据之上。我们还通过视觉模拟作为中间步骤展示了一个简单的综合分析实例，验证了RetroHolmes的诊断价值，并强调了基于物理的中间表示对物理推理的重要性。
英文摘要
Vision-Language Models (VLMs) are widely used for visual understanding, yet current evaluation protocols fail to assess whether these capabilities are grounded in physical reasoning. To address this gap, we introduce Retrospective Physical Process Reasoning, a new evaluation paradigm to reason backward from outcomes under explicit physical constraints. Building on the paradigm, we present RetroHolmes, the first real-world benchmark for Retrospective Physical Process Reasoning, comprising object-centric image pairs annotated with reachability labels and causal step sequences across diverse physical transitions. Using RetroHolmes, we analyze VLMs and uncover systematic failure modes, including judgment bias in reachability assessment and belief dominance over physical evidence, mirroring sycophancy behavior observed in large language models. Our quantitative analyses link these failures to reliance on linguistic priors and attention concentrated on visually invariant regions, suggesting limited physical simulation of the intermediate states connecting visual endpoints. To address these limitations, we propose Simulate-and-Verify, an analysis-by-synthesis framework that grounds reachability judgment and step reconstruction in visual simulation. Experiments show that Simulate-and-Verify improves judgment accuracy by 21.67 percentage points and reduces belief dominance by 10.39 percentage points compared with GPT-5.5, demonstrating the effectiveness of visual simulation in grounding physical reasoning.
