RecNet
Ctrl+K
About
Help
All Users
Log In
Back
Yoav Artzi
5/13/2025
Very simple, and very elegant approach to train LMs that have better planning ability. Interesting results, a lot to think about in terms of scaling.
The Belief State Transformer
Edward S. Hu, Kwangjun Ahn, Qinghua Liu, Haoran Xu, Manan Tomar, Ada Langford, Dinesh Jayaraman, Alex Lamb, John Langford
arxiv.org
1.17.1
Checking API service...
© 2024 RecNet. All rights reserved.