all AI news
BAGEL: Bootstrapping Agents by Guiding Exploration with Language
March 14, 2024, 4:48 a.m. | Shikhar Murty, Christopher Manning, Peter Shaw, Mandar Joshi, Kenton Lee
cs.CL updates on arXiv.org arxiv.org
Abstract: Following natural language instructions by executing actions in digital environments (e.g. web-browsers and REST APIs) is a challenging task for language model (LM) agents. Unfortunately, LM agents often fail to generalize to new environments without human demonstrations. This work presents BAGEL, a method for bootstrapping LM agents without human supervision. BAGEL converts a seed set of randomly explored trajectories or synthetic instructions, into demonstrations, via round-trips between two noisy LM components: an LM labeler which …
abstract agents apis arxiv bootstrapping browsers cs.cl digital environments exploration human language language model natural natural language rest type web work
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Intelligence Manager
@ Sanofi | Budapest
Principal Engineer, Data (Hybrid)
@ Homebase | Toronto, Ontario, Canada