Long-context Memory Management on LoCoMo (Precision, Recall, F1, Occupancy, Reward)
31.3Precision
OSL-MR
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.06 | 31.3 | 35.87 | 29.52 | 73.67 | 252.7 | |
2026.06 | 27.41 | 53.2 | 30.23 | 76.38 | 305.16 | |
2026.06 | 23.03 | 44.41 | 25.56 | 78.97 | 260.91 | |
2026.06 | 22.3 | 24.06 | 20.61 | 76.32 | 196.83 | |
2026.06 | 11.8 | 10.83 | 10.15 | 66.83 | 145.56 | |
2026.06 | 9.68 | 8.26 | 8.11 | 65.67 | 137.06 | |
2026.06 | 3.91 | 33.75 | 6.85 | 99.56 | 132.48 | |
2026.06 | 3.25 | 15.55 | 5.22 | 99.2 | 112.4 | |
2026.06 | 2.43 | 6.99 | 3.52 | 97.89 | 110.79 | |
2026.06 | 0.41 | 5.08 | 0.74 | 98.98 | 9.99 | |
2026.06 | 0.38 | 3.02 | 0.68 | 98.08 | 67.68 | |
2026.06 | 0.3 | 3.98 | 0.56 | 99.05 | 6.4 | |
2026.06 | 0.26 | 1 | 0.41 | 96.82 | 95.04 | |
2026.06 | 0.22 | 1.23 | 0.36 | 98.35 | 63.68 | |
2026.06 | 0.17 | 0.62 | 0.26 | 96.37 | 94.41 | |
2026.06 | 0.12 | 1.45 | 0.21 | 99.19 | 0 | |
2026.06 | 0.1 | 0.62 | 0.17 | 98.9 | 61.95 | |
2026.06 | 0 | 0 | 0 | 98.06 | 92.44 |