all AI news
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
March 14, 2024, 4:43 a.m. | Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin
cs.LG updates on arXiv.org arxiv.org
Abstract: Closed-source agents suffer from several issues such as a lack of affordability, transparency, and reproducibility, particularly on complex interactive tasks. This motivates the development of open-source alternatives. We introduce LUMOS, one of the first frameworks for training open-source LLM-based agents. LUMOS features a learnable, unified, and modular architecture with a planning module that learns high-level subgoal generation, and a grounding module trained to translate these into actions using various tools in the execution module. The …
abstract agent agents arxiv cs.ai cs.cl cs.lg development features frameworks interactive language llm modular reproducibility tasks training transparency type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Sr. Software Development Manager, AWS Neuron Machine Learning Distributed Training
@ Amazon.com | Cupertino, California, USA