List your company

Class-level Continual Learning on 2Wiki

71.74Average Accuracy (AA)MasFACT
37.960846.730455.564.2696May 17, 2026

Evaluation results

MethodLinks
MasFACTSetting=Standard, Replay-based=false2026.0571.740.08
MasFACTEvaluation Style=Standard2026.0571.740.08
MasRouterSetting=Standard, Replay-based=true2026.0570.172.06
MasRouter†Evaluation Style=Standard, Replay=true2026.0570.172.06
MasFACTSetting=Few-shot, Replay-based=false2026.0569.92-0.26
MasFACTEvaluation Style=Few-shot2026.0569.92-0.26
GDesignerSetting=Standard, Replay-based=true2026.0569.842.17
GDesigner†Evaluation Style=Standard, Replay=true2026.0569.842.17
MasRouterSetting=Few-shot, Replay-based=true2026.0569.161.41
MasRouter†Evaluation Style=Few-shot, Replay=true2026.0569.161.41
GDesignerSetting=Few-shot, Replay-based=true2026.0567.791.84
GDesigner†Evaluation Style=Few-shot, Replay=true2026.0567.791.84
MasRouterSetting=Standard, Replay-based=false2026.0567.513.62
ARGDesignerSetting=Standard, Replay-based=true2026.0567.512.08
MasRouterEvaluation Style=Standard2026.0567.513.62
ARGDesigner†Evaluation Style=Standard, Replay=true2026.0567.512.08
GDesignerSetting=Standard, Replay-based=false2026.0566.273.63
GDesignerEvaluation Style=Standard2026.0566.273.63
ARGDesignerSetting=Few-shot, Replay-based=true2026.0565.361.65
ARGDesigner†Evaluation Style=Few-shot, Replay=true2026.0565.361.65
MasRouterSetting=Few-shot, Replay-based=false2026.0565.282.84
MasRouterEvaluation Style=Few-shot2026.0565.282.84
GDesignerSetting=Few-shot, Replay-based=false2026.0565.092.74
GDesignerEvaluation Style=Few-shot2026.0565.092.74
AFLOWSetting=Standard, Replay-based=true2026.0564.732.29
AFLOW†Evaluation Style=Standard, Replay=true2026.0564.732.29
ARGDesignerSetting=Standard, Replay-based=false2026.0563.913.39
ARGDesignerEvaluation Style=Standard2026.0563.913.39
AgentDropoutSetting=Standard, Replay-based=true2026.0563.581.1
AgentDropout†Evaluation Style=Standard, Replay=true2026.0563.581.1
AFLOWSetting=Few-shot, Replay-based=true2026.0563.062.16
AFLOW†Evaluation Style=Few-shot, Replay=true2026.0563.062.16
AgentDropoutSetting=Few-shot, Replay-based=true2026.0562.941.53
AgentDropout†Evaluation Style=Few-shot, Replay=true2026.0562.941.53
AgentDropoutSetting=Standard, Replay-based=false2026.0562.841.97
AgentDropoutEvaluation Style=Standard2026.0562.841.97
ARGDesignerSetting=Few-shot, Replay-based=false2026.0562.412.94
ARGDesignerEvaluation Style=Few-shot2026.0562.412.94
AFLOWSetting=Standard, Replay-based=false2026.0561.973.45
AFLOWEvaluation Style=Standard2026.0561.973.45
AFLOWSetting=Few-shot, Replay-based=false2026.0560.482.9
AFLOWEvaluation Style=Few-shot2026.0560.482.9
AgentDropoutSetting=Few-shot, Replay-based=false2026.0560.071.81
AgentDropoutEvaluation Style=Few-shot2026.0560.071.81
SC(CoT)-ICLSetting=Few-shot, Replay-based=false2026.0558.362.15
SC(CoT)-ICLEvaluation Style=Few-shot2026.0558.362.15
CompleteSetting=Few-shot, Replay-based=false2026.0554.68—
CompleteEvaluation Style=Few-shot2026.0554.68—
TreeSetting=Few-shot, Replay-based=false2026.0552.74—
TreeEvaluation Style=Few-shot2026.0552.74—
ChainSetting=Few-shot, Replay-based=false2026.0550.62—
ChainEvaluation Style=Few-shot2026.0550.62—
CoT-ICLSetting=Few-shot, Replay-based=false2026.0550.582.61
CoT-ICLEvaluation Style=Few-shot2026.0550.582.61
VanillaSetting=Few-shot, Replay-based=false2026.0539.26—
VanillaEvaluation Style=Few-shot2026.0539.26—