List your company

Semantic Trap on OpenAgent Tier-1

28.6Accuracy DeltaSFT-200 + PAFT
-71.552-45.551-19.556.451Jul 1, 2026

Evaluation results

MethodLinks
SFT-200 + PAFTtraining_steps=200, PAFT=true2026.0728.6
SFT-400 + PAFTtraining_steps=400, PAFT=true2026.075.6
SFT-600 + PAFTtraining_steps=600, PAFT=true2026.07-2.5
SFT-800 + PAFTtraining_steps=800, PAFT=true2026.07-4.1
PAFT (alpha=0.3 default)training_steps=800, perturbation_ratio=0.32026.07-4.1
PAFT (alpha=0.4)training_steps=800, perturbation_ratio=0.42026.07-5.3
PAFT (alpha=0.2)training_steps=800, perturbation_ratio=0.22026.07-6.9
PAFT (SRP only)training_steps=800, perturbation_ratio=0.3, component=SRP2026.07-14.9
Base2026.07-29.8
PAFT (EFP only)training_steps=800, perturbation_ratio=0.3, component=EFP2026.07-30.1
PAFT (SBP only)training_steps=800, perturbation_ratio=0.3, component=SBP2026.07-38.9
SFT-800training_steps=8002026.07-50.4
SFT-600training_steps=6002026.07-51.3
SFT-400training_steps=4002026.07-53.9
SFT-200training_steps=2002026.07-67.7