| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Generalized Planning | Logistics (Extrapolation) | Coverage26 | 17 | |
| Generalized Planning | Logistics (Interpolation) | Coverage100 | 17 | |
| Generalized Planning | Logistics (val) | Coverage100 | 17 | |
| Generalized Planning | Logistics | Scale100 | 12 | |
| Planning | Logistics unseen problems | Completion Rate100 | 11 | |
| Planning | Logistics known optimal problems | Optimal Solutions Ratio169 | 11 | |
| Planning | Logistics | Completion Rate100 | 9 | |
| Planning | Logistics | Planning Success Rate1 | 8 | |
| Trajectory recovery | Logistics | MSE0.449 | 6 | |
| Simultaneous Action and Motion Planning | Logistics ALL-DC | Solution Count16 | 6 | |
| Simultaneous Action and Motion Planning | Logistics ALL-DO | Solution Count17 | 6 | |
| Simultaneous Action and Motion Planning | Logistics OC-DC | Solution Count19.3 | 6 | |
| Simultaneous Action and Motion Planning | Logistics OC-DO | Solution Count18.3 | 6 | |
| Compositional Generalization | Logistics | P1100 | 6 | |
| Planning | Logistics (test) | Average Solving Time (s)2.15 | 5 | |
| Continuous Learning | Logistics Delta 1st to 4th | Delta P1 (pp)55.2 | 3 | |
| Continuous Learning | Logistics 4th Encounter | P1 Score100 | 3 | |
| Continuous Learning | Logistics 3rd Encounter | P1 Score87.5 | 3 | |
| Continuous Learning | Logistics 2nd Encounter | P182.5 | 3 | |
| Continuous Learning | Logistics 1st Encounter | P144.8 | 3 | |
| Planning Domain Learning | logistics Partial observability | |z ∩ x'|6 | 2 | |
| Planning Domain Learning | logistics Action traces | Intersection Size (|z ∩ x'|)6 | 2 | |
| Action Schema Induction | Logistics (aggregated instances 1-3) | Precision33.96 | 1 | |
| Token Efficiency | Logistics Ship. | JSON Compactness Count1,333 | 1 |