Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Michael Y., Van Durme, Benjamin, Andreas, Jacob, Jhamtani, Harsh
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.10304