Agentic Reasoning on ALFWorld (test)
97.7Success Rate
teacher top-K local support matching
Updated 22d ago
Evaluation Results
| Method | Links | |
|---|---|---|
| 97.7 | ||
2026.03 | 95.6 | |
2026.03 | 95.3 | |
| 95.3 | ||
2026.03 | 93.8 | |
2026.03 | 91.7 | |
2026.03 | 90.8 | |
2026.03 | 90.6 | |
2026.03 | 89.9 | |
2026.03 | 82.3 | |
2026.03 | 78.5 | |
2026.03 | 77.3 | |
2026.03 | 75.5 | |
2026.03 | 62.5 | |
2026.03 | 54.7 | |
2026.03 | 43.8 | |
2026.03 | 42.7 | |
2026.03 | 31.2 | |
2026.03 | 21.9 | |
2026.03 | 21.4 | |
2026.03 | 16.9 |