Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Bandit Optimization on fLLM
Loading...
35.6
Cumulative Regret
LLMP-Joint
29.8
68.95
108.1
147.25
Apr 7, 2026
Cumulative Regret
Updated 11d ago
Evaluation Results
Method
Method
Links
Cumulative Regret
LLMP-Joint
Seeds=5
2026.04
35.6
LLM-Bandit
Seeds=5
2026.04
36
LLMP-Bandit
Seeds=5
2026.04
40
LinUCB
Seeds=5
2026.04
43.2
Thompson
Seeds=5
2026.04
54.6
CGPUCB
Seeds=5
2026.04
65.6
Random
Seeds=5
2026.04
130.4
ZeroShot
Seeds=5
2026.04
180.6
Feedback
Search any
task
Search any
task