Artificial intelligencefromInfoQ22 hours agoOpenAI at QCon AI NYC: Fine Tuning the EnterpriseAgent RFT applies reinforcement fine-tuning to tool-using agents to improve multi-step, tool-mediated decision-making via graded rewards and trajectory-level credit assignment.
Artificial intelligencefromTechzine Global7 months agoMicrosoft expands fine-tuning capabilities in Azure AI FoundryMicrosoft's Azure AI Foundry introduces Reinforcement Fine-Tuning, enhancing model performance by up to 40% for specific organizational needs.