| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-Agent Path Finding (MAPF) | warehouse 161x63 | Success Rate100 | 31 | |
| Multi-Task Reinforcement Learning (LTL Instruction Following) | Warehouse Finite Horizon | Success Rate99 | 30 | |
| Multi-Task Reinforcement Learning (LTL Instruction Following) | Warehouse Infinite Horizon | Average Visits880.6 | 20 | |
| Offline Multi-agent Reinforcement Learning | Warehouse Small (11x20) | Mean Performance (N=2)5.97 | 6 | |
| Offline Multi-agent Reinforcement Learning | Warehouse Tiny (11x11) | Mean Performance (N=2)11.15 | 6 | |
| Mobile Manipulation | Warehouse Cross-room transfer v1 | AIKF14.3 | 5 | |
| Robotic Exploration | Warehouse Gazebo simulation (test) | Distance (m)86,942 | 5 | |
| Autonomous Robotic Exploration | Warehouse Gazebo simulation (environment) | Exploration Distance (m)869 | 5 | |
| Multi-agent coordination | Warehouse (uneven) size S | Success Rate100 | 5 | |
| Multi-agent coordination | Warehouse (even) size S | Success Rate1 | 5 | |
| Mobile Manipulation | Warehouse | AIKF Score7.1 | 4 | |
| NL-to-TL Translation | Warehouse | LE Accuracy100 | 4 | |
| Multi-agent coordination | Warehouse uneven size (evaluation) | Success Rate0.84 | 4 | |
| Multi-agent coordination | Warehouse even size (evaluation) | Success Rate90 | 4 | |
| Object Rearrangement | Warehouse 40 m × 40 m (simulation) | Bin Success Rate100 | 1 |