Agent Memory Retrieval on LoCoMo (test)
27.56Multi-hop BLEU
xMemory
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 27.56 | 39.97 | 46.1 | 57.62 | 25.53 | 30.92 | 41.14 | 52.63 | 38.71 | 50 | 6,581.2 | |
2026.02 | 27.24 | 38.57 | 29.58 | 37.46 | 15.55 | 20.69 | 40.94 | 50.94 | 34.48 | 43.98 | 4,711.29 | |
2026.02 | 25.33 | 34.19 | 43.37 | 57.12 | 23.57 | 29.45 | 39.01 | 45.45 | 36.45 | 44.82 | 6,850.04 | |
2026.02 | 24.8 | 37.11 | 41.56 | 54.25 | 22.61 | 29.29 | 40.35 | 51.67 | 36.65 | 48.17 | 9,154.76 | |
2026.02 | 24.2 | 36.68 | 23.6 | 33.74 | 12.71 | 18.48 | 33.48 | 45.49 | 28.51 | 40.45 | 7,754.66 | |
2026.02 | 22.64 | 34.39 | 17.03 | 21.18 | 12.52 | 17.01 | 35.62 | 45.15 | 27.92 | 36.42 | 6,613.17 | |
2026.02 | 22.21 | 30.99 | 21.2 | 27.42 | 11.58 | 14.61 | 28.43 | 41.15 | 24.73 | 34.77 | 5,539.97 | |
2026.02 | 21.64 | 32.11 | 38.43 | 49.05 | 22.3 | 26.42 | 36.18 | 46.04 | 33.12 | 42.89 | 7,531.46 | |
2026.02 | 19.67 | 26.26 | 22.62 | 27.66 | 7.8 | 11.78 | 27.4 | 34.74 | 23.77 | 30.28 | 5,545.35 | |
2026.02 | 18.18 | 26.3 | 19.23 | 26.09 | 9.24 | 12.06 | 26.19 | 40.18 | 22.21 | 32.95 | 14,802.69 | |
2026.02 | 17.12 | 21.74 | 26.84 | 32.26 | 14.53 | 16.25 | 35.83 | 40.37 | 29.2 | 33.76 | 7,234.66 | |
2026.02 | 16.43 | 23.76 | 12.44 | 15.61 | 9.83 | 13.7 | 21.68 | 25.08 | 18.05 | 22.15 | 5,708.11 | |
2026.02 | 15.88 | 20.9 | 19.92 | 24.91 | 9.92 | 11.34 | 24.86 | 39.9 | 21.52 | 31.51 | 10,268.77 | |
2026.02 | 14.6 | 21.31 | 31 | 38.58 | 14.27 | 16.78 | 24.04 | 28.59 | 23.15 | 28.6 | 9,610.94 | |
2026.02 | 14.43 | 18.43 | 26.76 | 30.91 | 17 | 18.74 | 31.74 | 35.38 | 26.57 | 30.27 | 7,029.02 | |
2026.02 | 13.77 | 19.4 | 6.2 | 8.61 | 6.99 | 10.22 | 21.9 | 35.37 | 16.21 | 25.3 | 11,522.6 | |
2026.02 | 13.26 | 17.83 | 19.88 | 23.95 | 11.48 | 12.92 | 24.76 | 28.67 | 20.81 | 24.72 | 7,212.07 | |
2026.02 | 9.2 | 9.06 | 22.46 | 32.99 | 9.01 | 8.57 | 23.01 | 23.28 | 19.49 | 21.78 | 9,103.46 |