List your company

Class-level Continual Learning on MATH

61.68Average Accuracy (AA)MasFACT
34.754441.744748.73555.7253May 17, 2026

Evaluation results

MethodLinks
MasFACTSetting=Standard, Replay-based=false2026.0561.680.21
MasFACTEvaluation Style=Standard2026.0561.680.21
MasRouterSetting=Standard, Replay-based=true2026.0558.561.47
MasRouter†Evaluation Style=Standard, Replay=true2026.0558.561.47
ARGDesignerSetting=Standard, Replay-based=true2026.0557.831.59
ARGDesigner†Evaluation Style=Standard, Replay=true2026.0557.831.59
ARGDesignerSetting=Standard, Replay-based=false2026.0556.333.86
ARGDesignerEvaluation Style=Standard2026.0556.333.86
GDesignerSetting=Standard, Replay-based=true2026.0556.181.94
GDesigner†Evaluation Style=Standard, Replay=true2026.0556.181.94
MasFACTSetting=Few-shot, Replay-based=false2026.0556.07-0.45
MasFACTEvaluation Style=Few-shot2026.0556.07-0.45
MasRouterSetting=Few-shot, Replay-based=true2026.0555.172.76
MasRouter†Evaluation Style=Few-shot, Replay=true2026.0555.172.76
GDesignerSetting=Few-shot, Replay-based=true2026.0554.72.36
GDesigner†Evaluation Style=Few-shot, Replay=true2026.0554.72.36
MasRouterSetting=Standard, Replay-based=false2026.0554.284.46
MasRouterEvaluation Style=Standard2026.0554.284.46
ARGDesignerSetting=Few-shot, Replay-based=true2026.0554.211.88
ARGDesigner†Evaluation Style=Few-shot, Replay=true2026.0554.211.88
ARGDesignerSetting=Few-shot, Replay-based=false2026.0553.843.62
ARGDesignerEvaluation Style=Few-shot2026.0553.843.62
GDesignerSetting=Standard, Replay-based=false2026.0553.364.95
GDesignerEvaluation Style=Standard2026.0553.364.95
MasRouterSetting=Few-shot, Replay-based=false2026.0552.423.14
MasRouterEvaluation Style=Few-shot2026.0552.423.14
GDesignerSetting=Few-shot, Replay-based=false2026.0551.923.89
GDesignerEvaluation Style=Few-shot2026.0551.923.89
AgentDropoutSetting=Standard, Replay-based=true2026.0551.752.42
AgentDropout†Evaluation Style=Standard, Replay=true2026.0551.752.42
AgentDropoutSetting=Standard, Replay-based=false2026.0549.884.96
AgentDropoutEvaluation Style=Standard2026.0549.884.96
AFLOWSetting=Standard, Replay-based=true2026.0549.631.75
AFLOW†Evaluation Style=Standard, Replay=true2026.0549.631.75
AFLOWSetting=Standard, Replay-based=false2026.0548.853.92
AFLOWEvaluation Style=Standard2026.0548.853.92
AgentDropoutSetting=Few-shot, Replay-based=true2026.0547.051.56
AgentDropout†Evaluation Style=Few-shot, Replay=true2026.0547.051.56
AFLOWSetting=Few-shot, Replay-based=true2026.0544.392.03
AFLOW†Evaluation Style=Few-shot, Replay=true2026.0544.392.03
AgentDropoutSetting=Few-shot, Replay-based=false2026.0543.544.18
AgentDropoutEvaluation Style=Few-shot2026.0543.544.18
AFLOWSetting=Few-shot, Replay-based=false2026.0542.183.37
AFLOWEvaluation Style=Few-shot2026.0542.183.37
SC(CoT)-ICLSetting=Few-shot, Replay-based=false2026.0537.886.16
SC(CoT)-ICLEvaluation Style=Few-shot2026.0537.886.16
CompleteSetting=Few-shot, Replay-based=false2026.0537.63—
CompleteEvaluation Style=Few-shot2026.0537.63—
ChainSetting=Few-shot, Replay-based=false2026.0536.92—
ChainEvaluation Style=Few-shot2026.0536.92—
CoT-ICLSetting=Few-shot, Replay-based=false2026.0536.834.29
CoT-ICLEvaluation Style=Few-shot2026.0536.834.29
TreeSetting=Few-shot, Replay-based=false2026.0536.73—
TreeEvaluation Style=Few-shot2026.0536.73—
VanillaSetting=Few-shot, Replay-based=false2026.0535.79—
VanillaEvaluation Style=Few-shot2026.0535.79—