List your company

Continual Learning on Knowledge QA Domain-level stream

51.59AA ScoreMasFACT
24.529231.554638.5845.6054May 17, 2026

Evaluation results

MethodLinks
MasFACTReplay-based=false2026.0551.590.06
MasFACTReplay-based=false2026.0551.590.06
MasRouterReplay-based=true2026.0549.163.01
MasRouterReplay-based=true2026.0549.163.01
ARGDesignerReplay-based=true2026.0548.73.16
ARGDesignerReplay-based=true2026.0548.73.16
GDesignerReplay-based=true2026.0547.734.2
GDesignerReplay-based=true2026.0547.734.2
ARGDesignerReplay-based=false2026.0547.115.36
ARGDesignerReplay-based=false2026.0547.115.36
MasRouterReplay-based=false2026.0546.844.64
MasRouterReplay-based=false2026.0546.844.64
GDesignerReplay-based=false2026.0545.626.33
GDesignerReplay-based=false2026.0545.626.33
AgentDropoutReplay-based=true2026.0536.054.07
AgentDropoutReplay-based=true2026.0536.054.07
CoT-ICLReplay-based=false2026.0534.375.08
CoT-ICLReplay-based=false2026.0534.375.08
AgentDropoutReplay-based=false2026.0533.155.83
AgentDropoutReplay-based=false2026.0533.155.83
SC(CoT)-ICLReplay-based=false2026.0532.547.46
SC(CoT)-ICLReplay-based=false2026.0532.547.46
CompleteReplay-based=false2026.0532.24—
Complete GraphReplay-based=false2026.0532.24—
TreeReplay-based=false2026.0530.4—
TreeReplay-based=false2026.0530.4—
AFLOWReplay-based=true2026.0530.213.89
AFLOWReplay-based=true2026.0530.213.89
ChainReplay-based=false2026.0529.11—
ChainReplay-based=false2026.0529.11—
AFLOWReplay-based=false2026.0528.457.52
AFLOWReplay-based=false2026.0528.457.52
VanillaReplay-based=false2026.0525.57—
VanillaReplay-based=false2026.0525.57—