Task and Scenario Goal Completion on AppWorld normal (test)
91.2Task Goal Completion
Trajectory-Informed Memory Generation
Updated 5d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| 91.2 | 89.5 | - | ||
| 73.2 | 64.3 | - | ||
| 70.8 | 56.2 | - | ||
2025.10 | 61.3 | 39.3 | - | |
2025.10 | 60.7 | 44.6 | - | |
| 58.7 | 47.6 | - | ||
2025.10 | 58.3 | 41.1 | - | |
2025.10 | 56 | 33.9 | - | |
2025.10 | 54.8 | 33.9 | - | |
2025.10 | 49.4 | 33.9 | - | |
2026.04 | 48.8 | - | - | |
2026.04 | 33.2 | - | - | |
2026.04 | 20.8 | - | - | |
2026.04 | 8.9 | - | 5.5 | |
2026.04 | 7.1 | - | 4.1 | |
2026.04 | 5.9 | - | 3.3 | |
2026.04 | 5.4 | - | 2.8 | |
2026.04 | 3 | - | 1.3 |