Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Action Prediction on ALFWorld in domain
Loading...
95
Success Rate
GRPO
81.48
84.99
88.5
92.01
Jun 25, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
GRPO
Model=Qwen3-8B
2026.06
95
ours
Model=Qwen3-8B
2026.06
95
ours
Model=Qwen3-4B
2026.06
83
GRPO
Model=Qwen3-4B
2026.06
82
Feedback
Search any
task
Search any
task
