Class-level Continual Learning on 2Wiki
71.74Average Accuracy (AA)MasFACT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MasFACTSetting=Standard, Replay-based=false2026.05 | 71.74 | 0.08 | |
| MasFACTEvaluation Style=Standard2026.05 | 71.74 | 0.08 | |
| MasRouterSetting=Standard, Replay-based=true2026.05 | 70.17 | 2.06 | |
| MasRouter†Evaluation Style=Standard, Replay=true2026.05 | 70.17 | 2.06 | |
| MasFACTSetting=Few-shot, Replay-based=false2026.05 | 69.92 | -0.26 | |
| MasFACTEvaluation Style=Few-shot2026.05 | 69.92 | -0.26 | |
| GDesignerSetting=Standard, Replay-based=true2026.05 | 69.84 | 2.17 | |
| GDesigner†Evaluation Style=Standard, Replay=true2026.05 | 69.84 | 2.17 | |
| MasRouterSetting=Few-shot, Replay-based=true2026.05 | 69.16 | 1.41 | |
| MasRouter†Evaluation Style=Few-shot, Replay=true2026.05 | 69.16 | 1.41 | |
| GDesignerSetting=Few-shot, Replay-based=true2026.05 | 67.79 | 1.84 | |
| GDesigner†Evaluation Style=Few-shot, Replay=true2026.05 | 67.79 | 1.84 | |
| MasRouterSetting=Standard, Replay-based=false2026.05 | 67.51 | 3.62 | |
| ARGDesignerSetting=Standard, Replay-based=true2026.05 | 67.51 | 2.08 | |
| MasRouterEvaluation Style=Standard2026.05 | 67.51 | 3.62 | |
| ARGDesigner†Evaluation Style=Standard, Replay=true2026.05 | 67.51 | 2.08 | |
| GDesignerSetting=Standard, Replay-based=false2026.05 | 66.27 | 3.63 | |
| GDesignerEvaluation Style=Standard2026.05 | 66.27 | 3.63 | |
| ARGDesignerSetting=Few-shot, Replay-based=true2026.05 | 65.36 | 1.65 | |
| ARGDesigner†Evaluation Style=Few-shot, Replay=true2026.05 | 65.36 | 1.65 | |
| MasRouterSetting=Few-shot, Replay-based=false2026.05 | 65.28 | 2.84 | |
| MasRouterEvaluation Style=Few-shot2026.05 | 65.28 | 2.84 | |
| GDesignerSetting=Few-shot, Replay-based=false2026.05 | 65.09 | 2.74 | |
| GDesignerEvaluation Style=Few-shot2026.05 | 65.09 | 2.74 | |
| AFLOWSetting=Standard, Replay-based=true2026.05 | 64.73 | 2.29 | |
| AFLOW†Evaluation Style=Standard, Replay=true2026.05 | 64.73 | 2.29 | |
| ARGDesignerSetting=Standard, Replay-based=false2026.05 | 63.91 | 3.39 | |
| ARGDesignerEvaluation Style=Standard2026.05 | 63.91 | 3.39 | |
| AgentDropoutSetting=Standard, Replay-based=true2026.05 | 63.58 | 1.1 | |
| AgentDropout†Evaluation Style=Standard, Replay=true2026.05 | 63.58 | 1.1 | |
| AFLOWSetting=Few-shot, Replay-based=true2026.05 | 63.06 | 2.16 | |
| AFLOW†Evaluation Style=Few-shot, Replay=true2026.05 | 63.06 | 2.16 | |
| AgentDropoutSetting=Few-shot, Replay-based=true2026.05 | 62.94 | 1.53 | |
| AgentDropout†Evaluation Style=Few-shot, Replay=true2026.05 | 62.94 | 1.53 | |
| AgentDropoutSetting=Standard, Replay-based=false2026.05 | 62.84 | 1.97 | |
| AgentDropoutEvaluation Style=Standard2026.05 | 62.84 | 1.97 | |
| ARGDesignerSetting=Few-shot, Replay-based=false2026.05 | 62.41 | 2.94 | |
| ARGDesignerEvaluation Style=Few-shot2026.05 | 62.41 | 2.94 | |
| AFLOWSetting=Standard, Replay-based=false2026.05 | 61.97 | 3.45 | |
| AFLOWEvaluation Style=Standard2026.05 | 61.97 | 3.45 | |
| AFLOWSetting=Few-shot, Replay-based=false2026.05 | 60.48 | 2.9 | |
| AFLOWEvaluation Style=Few-shot2026.05 | 60.48 | 2.9 | |
| AgentDropoutSetting=Few-shot, Replay-based=false2026.05 | 60.07 | 1.81 | |
| AgentDropoutEvaluation Style=Few-shot2026.05 | 60.07 | 1.81 | |
| SC(CoT)-ICLSetting=Few-shot, Replay-based=false2026.05 | 58.36 | 2.15 | |
| SC(CoT)-ICLEvaluation Style=Few-shot2026.05 | 58.36 | 2.15 | |
| CompleteSetting=Few-shot, Replay-based=false2026.05 | 54.68 | — | |
| CompleteEvaluation Style=Few-shot2026.05 | 54.68 | — | |
| TreeSetting=Few-shot, Replay-based=false2026.05 | 52.74 | — | |
| TreeEvaluation Style=Few-shot2026.05 | 52.74 | — | |
| ChainSetting=Few-shot, Replay-based=false2026.05 | 50.62 | — | |
| ChainEvaluation Style=Few-shot2026.05 | 50.62 | — | |
| CoT-ICLSetting=Few-shot, Replay-based=false2026.05 | 50.58 | 2.61 | |
| CoT-ICLEvaluation Style=Few-shot2026.05 | 50.58 | 2.61 | |
| VanillaSetting=Few-shot, Replay-based=false2026.05 | 39.26 | — | |
| VanillaEvaluation Style=Few-shot2026.05 | 39.26 | — |