| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-agent system task solving | plancraft | Accuracy88.7 | 21 | |
| World Modeling | Plancraft | Smelt98.4 | 20 | |
| Planning and self-evolution under curriculum setting | PlanCraft | Success Rate (Easy)72.5 | 7 | |
| Sequential Planning | PlanCraft | Performance Change vs. SAS39.1 | 1 |