List your company

Embodied Task Planning on ALFWorld (134 evaluation environments)

10.42Cumulative ReturnLWM-Planner
-0.41682.39665.218.0234Jun 10, 2025

Evaluation results

MethodLinks
LWM-Plannerruns=single-seed, confidence_interval=95%2025.0610.42
ReAct + FECruns=single-seed, confidence_interval=95%2025.068.53
ReActruns=single-seed, confidence_interval=95%2025.065
Reflexionruns=single-seed, confidence_interval=95%2025.064.36
Randomruns=single-seed, confidence_interval=95%2025.060