List your company

Continual Learning on Math Domain-level stream

47.91AAMasFACT
28.534833.564938.59543.6251May 17, 2026

Evaluation results

MethodLinks
MasFACTReplay-based=false2026.0547.910.57
MasFACTReplay-based=false2026.0547.910.57
MasRouterReplay-based=true2026.0546.283.6
MasRouterReplay-based=true2026.0546.283.6
GDesignerReplay-based=true2026.0545.523.57
GDesignerReplay-based=true2026.0545.523.57
MasRouterReplay-based=false2026.0543.864.02
MasRouterReplay-based=false2026.0543.864.02
GDesignerReplay-based=false2026.0542.935.14
GDesignerReplay-based=false2026.0542.935.14
AgentDropoutReplay-based=true2026.0541.174.92
AgentDropoutReplay-based=true2026.0541.174.92
ARGDesignerReplay-based=true2026.0540.47.59
ARGDesignerReplay-based=true2026.0540.47.59
AFLOWReplay-based=true2026.0540.294.16
AFLOWReplay-based=true2026.0540.294.16
AgentDropoutReplay-based=false2026.0539.595.62
AgentDropoutReplay-based=false2026.0539.595.62
AFLOWReplay-based=false2026.0539.466.89
AFLOWReplay-based=false2026.0539.466.89
ARGDesignerReplay-based=false2026.0538.943.93
ARGDesignerReplay-based=false2026.0538.943.93
CompleteReplay-based=false2026.0535.5—
Complete GraphReplay-based=false2026.0535.5—
TreeReplay-based=false2026.0534.29—
TreeReplay-based=false2026.0534.29—
SC(CoT)-ICLReplay-based=false2026.0533.826.24
SC(CoT)-ICLReplay-based=false2026.0533.826.24
ChainReplay-based=false2026.0530.63—
ChainReplay-based=false2026.0530.63—
CoT-ICLReplay-based=false2026.0530.196.13
CoT-ICLReplay-based=false2026.0530.196.13
VanillaReplay-based=false2026.0529.28—
VanillaReplay-based=false2026.0529.28—