https://www.infoq.com InfoQ Software Engineering News feed https://www.infoq.com/news/2025/12/qcon-openai-rft/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Software+Engineering-news <img src="https://www.infoq.com/styles/static/images/logo/logo_bigger.jpg"/><p>At QCon AI NYC 2025, Will Hang from OpenAI unveiled Agent RFT—a cutting-edge reinforcement fine-tuning approach for tool-using agents. By optimizing prompts and tasks before model adjustments, Hang showcased effective strategies to enhance decision-making and efficiency, emphasizing a balanced grading system. The session revealed a future where smarter agents reduce latency and improve outcomes.</p> <i>By Andrew Hoblitzell</i> QCon Software Development Conference QCon AI 2025 Software Engineering OpenAI Model Fine Tuning Artificial Intelligence AI, ML & Data Engineering news Wed, 17 Dec 2025 19:25:00 GMT https://www.infoq.com/news/2025/12/qcon-openai-rft/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Software+Engineering-news Andrew Hoblitzell 2025-12-17T19:25:00Z /news/2025/12/qcon-openai-rft/en