List your company

Instruction Execution on VirtualHome Unseen domains

83.61Success RateTMoW
39.264450.777262.2973.8028Jan 30, 2026

Evaluation results

MethodLinks
TMoWshot=5-Shot2026.0183.6112.04
TMoWshot=Average2026.0182.5912.62
TMoWshot=1-Shot2026.0181.5613.2
SayCanPayshot=5-Shot2026.0158.8816.92
SayCanPayshot=Average2026.0156.9317.35
SayCanPayshot=1-Shot2026.0154.9817.77
LLM+FTshot=5-Shot2026.0154.3618.55
LLM+FTshot=Average2026.0152.4119.03
LLM+FTshot=1-Shot2026.0150.4619.51
FLAREshot=5-Shot2026.0146.6420.67
LLM-Plannershot=5-Shot2026.0143.6121.06
LLM-Plannershot=Average2026.0143.321.45
FLAREshot=Average2026.0142.2921.56
FLAREshot=1-Shot2026.0142.1722.19
LLM-Plannershot=1-Shot2026.0140.9722.07