List your company

Multi-turn agent interaction on WebShop

89.06Success RateATOD
-2.751221.084444.9268.7556Jun 14, 2026Jun 16, 2026Jun 18, 2026Jun 20, 2026Jun 22, 2026Jun 24, 2026Jun 26, 2026

Evaluation results

MethodLinks
ATODStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-4B GRPO2026.0689.06—6.2
ATODStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-4B GRPO2026.0686.72—7.48
OPDStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-4B GRPO2026.0685.16—6.23
TCODStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-4B GRPO2026.0684.38—5.94
GRPOStudent Model=None, Teacher Model=Qwen3-4B GRPO2026.0682.03—6.21
GRPOStudent Model=Qwen3-4B, Teacher Model=None2026.0682.03—6.21
TCODStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-4B GRPO2026.0681.25—6.1
SODStudent Model=Qwen3-0.6B, Teacher Model=Qwen3-4B GRPO2026.0680.47—5.95
ATODStudent Model=Qwen3-4B, Teacher Model=Qwen3-30B-A3B GRPO2026.0678.91—8.29
OPDStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-4B GRPO2026.0677.34—6.15
SODStudent Model=Qwen3-1.7B, Teacher Model=Qwen3-4B GRPO2026.0676.56—5.59
SODStudent Model=Qwen3-4B, Teacher Model=Qwen3-30B-A3B GRPO2026.0676.56—6.68
GRPOStudent Model=None, Teacher Model=Qwen3-30B-A3B GRPO2026.0675.78—8.02
TCODStudent Model=Qwen3-4B, Teacher Model=Qwen3-30B-A3B GRPO2026.0675.78—9.21
OPDStudent Model=Qwen3-4B, Teacher Model=Qwen3-30B-A3B GRPO2026.0675—8.53
SDARStudent Model=Qwen3-4B, Teacher Model=None2026.0667.97—7.91
GRPOStudent Model=Qwen3-1.7B, Teacher Model=None2026.0647.66—10.01
SDARStudent Model=Qwen3-1.7B, Teacher Model=None2026.0643.75—8.9
GRPOStudent Model=Qwen3-0.6B, Teacher Model=None2026.0629.69—9.73
Zero-shotParams=30B-A3B2026.0619.2555.074.96
TCODParams=4B2026.061953.134.26
Guided-OPDParams=4B2026.0617.7555.784.28
TCODParams=1.7B2026.0614.2549.474.39
Vanilla OPDParams=4B2026.0613.550.874.53
AdaSwitchParams=4B2026.0612.3548.915.57
Guided-OPDParams=1.7B2026.0611.7552.634.14
Vanilla OPDParams=1.7B2026.061147.595.54
AdaSwitchParams=1.7B2026.0610.546.795.81
Zero-shotParams=1.7B2026.0610.2528.719.11
Guided-OPDParams=0.6B2026.069.7548.444.8
SDARStudent Model=Qwen3-0.6B, Teacher Model=None2026.068.59—10.27
TCODParams=0.6B2026.068.2546.373.83
Zero-shotParams=4B2026.068.2520.5912.23
Vanilla OPDParams=0.6B2026.06839.896.95
AdaSwitchParams=0.6B2026.067.7543.415.08
VanillaStudent Model=Qwen3-1.7B, Teacher Model=None2026.065.47—8.43
VanillaStudent Model=Qwen3-0.6B, Teacher Model=None2026.064.69—9.59
Zero-shotParams=0.6B2026.063.7510.3714.03
VanillaStudent Model=Qwen3-4B, Teacher Model=None2026.060.78—13.99