Response Generation on Chronicle and MSC Average
70.3CEAEventWeave
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| EventWeaveBackbone=GPT-o12025.03 | 70.3 | 57.6 | 59.7 | 62.7 | |
| EventWeaveBackbone=DeepSeek-R12025.03 | 68.8 | 56.5 | 58.6 | 61.5 | |
| EventWeaveBackbone=DeepSeek-V32025.03 | 67.7 | 55.4 | 57.5 | 60.4 | |
| EventWeaveBackbone=Qwen3-14B2025.03 | 67.2 | 54.9 | 57.1 | 60 | |
| EventWeaveBackbone=Qwen2.5-14B2025.03 | 65.8 | 53.7 | 55.9 | 58.7 | |
| LifeLongMemBackbone=GPT-o12025.03 | 54.1 | 45.8 | 47.4 | 50.1 | |
| LifeLongMemBackbone=DeepSeek-R12025.03 | 52.9 | 44.8 | 46.4 | 49 | |
| LifeLongMemBackbone=DeepSeek-V32025.03 | 51.8 | 43.7 | 45.3 | 47.8 | |
| LifeLongMemBackbone=Qwen3-14B2025.03 | 51.4 | 43.3 | 45 | 47.5 | |
| LifeLongMemBackbone=Qwen2.5-14B2025.03 | 50.1 | 42.2 | 43.8 | 46.3 | |
| MemWalkerBackbone=GPT-o12025.03 | 49.7 | 41.3 | 43.7 | 46.2 | |
| MemWalkerBackbone=DeepSeek-R12025.03 | 48.5 | 40.4 | 42.8 | 45.2 | |
| MemWalkerBackbone=DeepSeek-V32025.03 | 47.4 | 39.3 | 41.7 | 44.1 | |
| LongMemBackbone=GPT-o12025.03 | 47.3 | 39.9 | 41.4 | 43.9 | |
| MemWalkerBackbone=Qwen3-14B2025.03 | 47 | 39 | 41.4 | 43.8 | |
| LongMemBackbone=DeepSeek-R12025.03 | 46.1 | 39 | 40.5 | 42.9 | |
| MemWalkerBackbone=Qwen2.5-14B2025.03 | 45.7 | 37.9 | 40.3 | 42.6 | |
| LongMemBackbone=DeepSeek-V32025.03 | 45 | 37.9 | 39.4 | 41.8 | |
| LongMemBackbone=Qwen3-14B2025.03 | 44.6 | 37.6 | 39.1 | 41.5 | |
| ProactiveCoTBackbone=GPT-o12025.03 | 44 | 37 | 37.5 | 39.7 | |
| LongMemBackbone=Qwen2.5-14B2025.03 | 43.4 | 36.5 | 38 | 40.3 | |
| ProactiveCoTBackbone=DeepSeek-R12025.03 | 42.8 | 36.1 | 36.6 | 38.7 | |
| ProactiveCoTBackbone=DeepSeek-V32025.03 | 41.7 | 35 | 35.7 | 37.8 | |
| ProactiveCoTBackbone=Qwen3-14B2025.03 | 41.3 | 34.7 | 35.4 | 37.5 | |
| ProactiveCoTBackbone=Qwen2.5-14B2025.03 | 40.1 | 33.6 | 34.2 | 36.3 | |
| GPT-o1Strategy=vanilla2025.03 | 29.8 | 21.5 | 22.6 | 25 | |
| DeepSeek-R1Strategy=vanilla2025.03 | 28.9 | 20.6 | 21.7 | 24 | |
| DeepSeek-V3Strategy=vanilla2025.03 | 28 | 19.8 | 21 | 23.2 | |
| Qwen3-14BStrategy=vanilla2025.03 | 27.5 | 19.6 | 20.7 | 22.8 | |
| Qwen2.5-14BStrategy=vanilla2025.03 | 26.4 | 18.7 | 19.8 | 21.9 |