Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs
Paper
•
2510.07429
•
Published
•
3
rtfvbhkuj
wwdd7718
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
18 days ago
Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs
liked
a dataset
6 months ago
withmartian/routerbench
upvoted
a
paper
7 months ago
Efficient Model Selection for Time Series Forecasting via LLMs
Organizations
None yet