Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models725Deals30d248Policy30d59, 11 pendingSources984
Tuesday, September 29, 20261 min read← AI WIRE

CoreWeave Open-Sources Agent Reinforcement Trainer for LLM Agents

CoreWeave released ART, an open-source reinforcement learning framework for training LLM agents, with support for rollouts, rewards, GRPO, and W&B…

BY THE PRO DESKED. U. AHMADALERTIndustry ProSINGLE SOURCE · via www.coreweave.com

CoreWeave released Agent Reinforcement Trainer (ART), an open-source framework for training large language model agents using reinforcement learning1. ART includes support for rollouts, rewards, Group Relative Policy Optimization (GRPO), and Weights & Biases integration.