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 Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York