Despite increasing interest in using LLMs for robotics and agent reasoning, current evaluations are fragmented and often limited to final task success rates. These approaches fail to reveal specific reasoning failures, limiting scientific understanding and practical progress.

The **Embodied Agent Interface** addresses this gap through a **modular evaluation framework** that standardizes task interfaces and metrics across four core decision-making abilities:

- **Goal Interpretation**  
- **Subgoal Decomposition**  
- **Action Sequencing**  
- **Transition Modeling**