List your company

Class-level Continual Learning on TACO

73.8AAMasFACT
53.7858.977564.17569.3725May 17, 2026

Evaluation results

MethodLinks
MasFACTSetting=Standard, Replay-based=false2026.0573.8-0.11
MasFACTEvaluation Style=Standard2026.0573.8-0.11
GDesignerSetting=Standard, Replay-based=true2026.0572.351.06
GDesigner†Evaluation Style=Standard, Replay=true2026.0572.351.06
MasRouterSetting=Standard, Replay-based=true2026.0571.572.25
MasRouter†Evaluation Style=Standard, Replay=true2026.0571.572.25
MasFACTSetting=Few-shot, Replay-based=false2026.0570.940.12
MasFACTEvaluation Style=Few-shot2026.0570.940.12
ARGDesignerSetting=Standard, Replay-based=true2026.0570.241.92
ARGDesigner†Evaluation Style=Standard, Replay=true2026.0570.241.92
MasRouterSetting=Few-shot, Replay-based=true2026.0569.762.89
MasRouter†Evaluation Style=Few-shot, Replay=true2026.0569.762.89
GDesignerSetting=Standard, Replay-based=false2026.0569.425.26
GDesignerEvaluation Style=Standard2026.0569.425.26
ARGDesignerSetting=Standard, Replay-based=false2026.0569.414.28
ARGDesignerEvaluation Style=Standard2026.0569.414.28
ARGDesignerSetting=Few-shot, Replay-based=true2026.0568.822.21
ARGDesigner†Evaluation Style=Few-shot, Replay=true2026.0568.822.21
MasRouterSetting=Standard, Replay-based=false2026.0568.753.7
MasRouterEvaluation Style=Standard2026.0568.753.7
MasRouterSetting=Few-shot, Replay-based=false2026.0567.623.12
MasRouterEvaluation Style=Few-shot2026.0567.623.12
ARGDesignerSetting=Few-shot, Replay-based=false2026.0567.363.74
ARGDesignerEvaluation Style=Few-shot2026.0567.363.74
GDesignerSetting=Few-shot, Replay-based=true2026.0567.12.22
GDesigner†Evaluation Style=Few-shot, Replay=true2026.0567.12.22
GDesignerSetting=Few-shot, Replay-based=false2026.0566.414.81
GDesignerEvaluation Style=Few-shot2026.0566.414.81
AgentDropoutSetting=Standard, Replay-based=true2026.0565.911.42
AgentDropout†Evaluation Style=Standard, Replay=true2026.0565.911.42
AFLOWSetting=Standard, Replay-based=true2026.0565.482.13
AFLOW†Evaluation Style=Standard, Replay=true2026.0565.482.13
AFLOWSetting=Few-shot, Replay-based=true2026.0564.752.64
AFLOW†Evaluation Style=Few-shot, Replay=true2026.0564.752.64
AFLOWSetting=Standard, Replay-based=false2026.0564.124.21
AFLOWEvaluation Style=Standard2026.0564.124.21
AgentDropoutSetting=Few-shot, Replay-based=true2026.0563.381.7
AgentDropout†Evaluation Style=Few-shot, Replay=true2026.0563.381.7
AgentDropoutSetting=Standard, Replay-based=false2026.0563.143.53
AgentDropoutEvaluation Style=Standard2026.0563.143.53
AFLOWSetting=Few-shot, Replay-based=false2026.0562.843.68
AFLOWEvaluation Style=Few-shot2026.0562.843.68
AgentDropoutSetting=Few-shot, Replay-based=false2026.0562.723.17
AgentDropoutEvaluation Style=Few-shot2026.0562.723.17
SC(CoT)-ICLSetting=Few-shot, Replay-based=false2026.0559.223.03
SC(CoT)-ICLEvaluation Style=Few-shot2026.0559.223.03
CompleteSetting=Few-shot, Replay-based=false2026.0559.01—
CompleteEvaluation Style=Few-shot2026.0559.01—
ChainSetting=Few-shot, Replay-based=false2026.0558.46—
ChainEvaluation Style=Few-shot2026.0558.46—
CoT-ICLSetting=Few-shot, Replay-based=false2026.0558.044.38
CoT-ICLEvaluation Style=Few-shot2026.0558.044.38
VanillaSetting=Few-shot, Replay-based=false2026.0555.15—
VanillaEvaluation Style=Few-shot2026.0555.15—
TreeSetting=Few-shot, Replay-based=false2026.0554.55—
TreeEvaluation Style=Few-shot2026.0554.55—