List your company

Interactive Decision Making on ALFWorld (Efficiency Metrics)

91.73Avg@4 (Least-Time)TurnOPD
-3.669221.097945.86570.6321Jul 7, 2026

Evaluation results

MethodLinks
TurnOPDStudent=Qwen3-4B, Teacher=Qwen3-8B-GRPO2026.0791.7392.212.161.33
Vanilla OPDStudent=Qwen3-4B, Teacher=Qwen3-8B-GRPO2026.0790.7991.812.861
TeacherStudent=Qwen3-1.7B, Teacher=Qwen3-8B-GRPO2026.0790.7590.75——
TeacherStudent=Qwen3-4B, Teacher=Qwen3-8B-GRPO2026.0790.7590.75——
TCOD-F2BStudent=Qwen3-4B, Teacher=Qwen3-8B-GRPO2026.0786.586.51.891.51
TurnOPDStudent=Qwen3-1.7B, Teacher=Qwen3-8B-GRPO2026.0785.686.291.932.29
TCOD-F2BStudent=Qwen3-1.7B, Teacher=Qwen3-8B-GRPO2026.0780.0680.061.872.37
Vanilla OPDStudent=Qwen3-1.7B, Teacher=Qwen3-8B-GRPO2026.0773.52834.421
Zero-ShotStudent=Qwen3-4B, Teacher=Qwen3-8B-GRPO2026.078.178.17——
Zero-ShotStudent=Qwen3-1.7B, Teacher=Qwen3-8B-GRPO2026.0700——