List your company

Embodied Task Planning on ALFWorld (seen domains)

72.05Success Rate (SR)TMoW
-0.469218.357937.18556.0121Jan 30, 2026

Evaluation results

MethodLinks
TMoWBackbone=Llama-3.2-1B2026.0172.056.94
LLM+FTBackbone=Llama-3.2-1B, Training=Fine-tuned2026.0151.7813.22
SayCanPaySay Backbone=Llama-3.2-3B, Pay Backbone=Llama-3.2-1B2026.0151.4813.19
FLAREBackbone=Llama-3.2-3B2026.0121.2234.4
LLM-PlannerBackbone=Llama-3.2-3B, Adaptation=Few-shot2026.0111.6737.19
ZSPBackbone=Llama-3.2-3B, Adaptation=Zero-shot2026.012.3249.34