Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical environments. However, existing benchmarks often prioritize high-level planning or spatial reasoning, leaving the fine-grained action intelligence required for embodied physical interaction underexplored. To address this gap, we introduce CFG-Bench, a new benchmark designed to systematically evaluate this crucial capability. CFG-Bench consists of 1,368 curated videos paired with 19,562 three-modalities question-answer pairs targeting four cognitive abilities: 1) Physical Interaction, 2) Temporal-Causal Relation, 3) Intentional Understanding, and 4) Evaluative Judgment. Together, these dimensions provide a systematic framework for assessing a model's ability to translate visual observations into actionable knowledge, moving beyond mere surface-level recognition. Our comprehensive evaluation on CFG-Bench reveals that leading MLLMs struggle to produce detailed instructions for physical interactions and exhibit profound limitations in the higher-order reasoning of intention and evaluation. Moreover, supervised fine-tuning (SFT) on our data demonstrates that teaching an MLLMs to articulate fine-grained actions directly translates to significant performance gains on established embodied benchmarks. Our analysis highlights these limitations and offers insights for developing more capable and grounded embodied agents.

翻译：多模态大语言模型（MLLMs）作为决策引擎，在复杂物理环境中运行的具身智能体展现出广阔前景。然而，现有基准评测通常侧重于高层规划或空间推理，对具身物理交互所需的细粒度动作智能探索不足。为填补这一空白，我们提出了CFG-Bench——一个旨在系统评估该关键能力的新基准。CFG-Bench包含1,368个精选视频及与之配对的19,562组三模态问答对，针对四项认知能力：1）物理交互，2）时序-因果关联，3）意图理解，4）评估性判断。这些维度共同构成了评估模型将视觉观察转化为可执行知识能力的系统框架，超越了表层识别。我们在CFG-Bench上的综合评估表明，主流MLLMs在生成物理交互的详细指令方面存在困难，且在意图与评估的高阶推理上表现出明显局限。此外，基于本数据的监督微调（SFT）证明，教导MLLMs表述细粒度动作能直接转化为在现有具身基准上的显著性能提升。我们的分析揭示了这些局限性，并为开发更具能力且具现实基础的具身智能体提供了洞见。