Published on October 8, 2025, Salesforce’s post presents UserRL, a framework for training agents with standardized environments and simulated users.
In a post published on October 8, 2025, Salesforce presents UserRL, a framework combining standardized gym environments and simulated users to train agentic models. The post reports findings on cold starts with SFT, trajectory rewards, and scalable training with simulated users.
According to the post, these training choices may inform the development of agents for multi-turn interactions. Consult Salesforce’s original text to check its full scope and findings; when using AI to study it, avoid submitting personal data or internal information without authorization.