## 🧪 Benchmark Overview

The benchmark dataset consists of:

- ✅ 338 tasks in **VirtualHome** across 26 categories
- ✅ 100 tasks in **BEHAVIOR** with complex physical goals
- ✅ LTL-annotated goals, symbolic trajectories, and PDDL-style transition models
- ✅ Support for interpretable and reproducible evaluation

## 🧩 Tasks & Abilities

Participants may compete in one or more of the following modules:

1. **Goal Interpretation**: Translate natural language into formal symbolic goals.
2. **Subgoal Decomposition**: Break down goals into executable substeps.
3. **Action Sequencing**: Generate feasible action trajectories to accomplish goals.
4. **Transition Modeling**: Infer preconditions and effects of symbolic actions.

Each module can be tackled independently, with leaderboards and evaluation scripts provided per module.