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

Embodied Task Completion on ALFWorld (Unseen tasks)

100Look Success Rate

Evolving-RL

-4235077May 11, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
10061.281.1
2026.05
95.681.288.6
2026.05
81.255.668.8
2026.05
67637.4
2026.05
61.127.144.6
2026.05
53.312.933.7
2026.05
18.936.527.4
2026.05
16.736.526.3
2026.05
11.135.322.9
2026.05
041.220