Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive Instruction Following on ALFWorld OOD
Loading...
92
Success Rate
Task-Perturbed NLL Optimization
23.568
41.334
59.1
76.866
Feb 2, 2026
Feb 25, 2026
Mar 21, 2026
Apr 14, 2026
May 8, 2026
Jun 1, 2026
Jun 25, 2026
Success Rate
Updated 29d ago
Evaluation Results
Method
Method
Links
Success Rate
Task-Perturbed NLL Optimization
Backbone=Qwen3-8B
2026.06
92
ProcMEM
2026.02
90.9
AWM
2026.02
90
GRPO
Backbone=Qwen3-8B
2026.06
86
G-Memory
2026.02
81.2
Expel
2026.02
74
ReAct
2026.02
64
A-MEM
2026.02
64
CoT
2026.02
62
Task-Perturbed NLL Optimization
Backbone=Qwen3-4B
2026.06
62
GRPO
Backbone=Qwen3-4B
2026.06
44
RAG
2026.02
40.2
State
2026.02
26.2
Feedback
Search any
task
Search any
task