List your company

Embodied AI task execution on ALFWorld OOD v1

0.994SRAgentMark
0.909760.931630.95350.97537Jan 5, 2026

Evaluation results

MethodLinks
AgentMarkTask=A1: Look At Obj In Light2026.010.994111.3830.30.07-0.0076
AgentMarkTask=A2: Pick And Place Simple2026.010.97913.61.3925.50.15-0.0022
AgentMarkTask=A4: Pick Cool Then Place2026.010.97614.31.1822.7-1.01-0.0011
AgentMarkTask=Avg.2026.010.97514.11.3428.4-0.18-0.003
AgentMarkTask=A6: Pick Two Obj And Place2026.010.97124.11.4138.2-0.18-0.0088
AgentMarkTask=A3: Pick Clean Then Place2026.010.96815.21.2924.5-0.180.0009
AgentMarkTask=A5: Pick Heat Then Place2026.010.91317.11.4433.40.02-0.0037