List your company

Tutor Robustness Evaluation on Base Student Adv. Agent

18Student LeakageMathDial-SFT
16.0829.044254.96Apr 20, 2026

Evaluation results

MethodLinks
MathDial-SFTTutor Setting=Base in-context2026.04184.77405.85
SocraticLMTutor Setting=Base in-context2026.04375.33342.49
TutorRL-7BTutor Setting=Base in-context2026.04665.95178.74