Make LLM Learn to Synthesize from Streaming Experiences through Feedback

ArXi:2605.29940v1 Announce Type: new Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a set of isolated tasks and overlook a fundamental question: whether a model can learn to synthesize by accumulating experience from past tasks and transferring it to future ones. In this work, we