List your company

E-commerce Interaction on WebShop 128 tasks (test)

89.4ScoreSDAR
-3.36820.71644.868.884Jun 25, 2026

Evaluation results

MethodLinks
SDARBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.0689.482.8
RLSDBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.0687.477.3
Skill-GRPOBackbone=Qwen2.5-7B-Instruct, Validation with skills=true2026.068781.2
GRPO+OPSDBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.0686.876.5
Skill-SDBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.0686.176.5
OPIDBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.0685.379.7
SDARBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.068568
OPIDBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.068574.2
RLSDBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.0684.466.4
Skill-SDBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0681.853.9
GRPOBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.0680.972.6
Skill-GRPOBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.0680.471.9
Skill-GRPOBackbone=Qwen3-1.7B-Instruct, Validation with skills=true2026.0680.450
GRPOBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.0679.863.3
OPIDBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0679.664.8
GRPO+OPSDBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.0677.866.4
Skill-GRPOBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.0677.360.9
SDARBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0676.858.6
Skill-GRPOBackbone=Qwen2.5-3B-Instruct, Validation with skills=true2026.0676.366.4
Skill-SDBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.0675.964
RLSDBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.067450.8
Skill-GRPOBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0673.446.1
GRPO+OPSDBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0670.738.3
GRPOBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0667.338.3
OPSDBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0647.49.3
VanillaBackbone=Qwen3-1.7B-Instruct, Validation with skills=false2026.0646.54.7
Skill-PromptBackbone=Qwen3-1.7B-Instruct, Validation with skills=true2026.06232.3
OPSDBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.0611.33.1
VanillaBackbone=Qwen2.5-3B-Instruct, Validation with skills=false2026.066.70.8
VanillaBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.065.91.6
OPSDBackbone=Qwen2.5-7B-Instruct, Validation with skills=false2026.064.52.3
Skill-PromptBackbone=Qwen2.5-7B-Instruct, Validation with skills=true2026.061.70.8
Skill-PromptBackbone=Qwen2.5-3B-Instruct, Validation with skills=true2026.060.20.8