Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sequential Decision Making on ALFWorld (post-training evaluation)
Loading...
43.9
Rollout Length
Starting policy
21.02
26.96
32.9
38.84
Jun 30, 2026
Rollout Length
Updated 25d ago
Evaluation Results
Method
Method
Links
Rollout Length
Starting policy
Backbone=Qwen2.5-7B-In...
2026.06
43.9
GRPO
Backbone=Qwen2.5-7B-In...
2026.06
24.45
TRIAGE
Backbone=Qwen2.5-7B-In...
2026.06
21.9
Feedback
Search any
task
Search any
task