Interactive Task Solving on ALFWorld Large context window
100Pick Success Rate
Embedding
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2026.06 | 100 | 3.2 | 50 | 0 | 77.8 | 35.3 | 42.5 | |
2026.06 | 100 | 67.7 | 78.3 | 33.3 | 72.2 | 76.5 | 71.6 | |
2026.06 | 95.8 | 61.3 | 82.6 | 14.3 | 83.3 | 88.2 | 70.1 | |
2026.06 | 95.8 | 35.5 | 87 | 0 | 77.8 | 64.7 | 59 | |
2026.06 | 95.8 | 54.8 | 78.3 | 14.3 | 77.8 | 70.6 | 64.9 | |
2026.06 | 95.8 | 6.5 | 47.8 | 0 | 77.8 | 41.2 | 42.5 | |
2026.06 | 91.7 | 0 | 47.8 | 4.8 | 55.6 | 11.8 | 34.3 | |
2026.06 | 79.2 | 83.9 | 60.9 | 95.2 | 66.7 | 47.1 | 73.9 |