Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Embodied Agent Task Completion on ALFWorld

7.8Success Rate Delta

ReasoningBank

-0.3121.7943.96.006Jun 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
7.8-20.1
2026.06
7.852.120.8
2026.06
6.947.420.9
2026.06
5.2-20.4
2026.06
465.717.3
2026.06
1.8-21
2026.06
040.522.3
2026.06
044.321.9
2026.06
061.717.9