نسخة أولية وصول مفتوح
When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain
Self-evolution lets large language models (LLMs) improve iteratively using their own generated data, but often suffers from self-evolution degeneration: performance improves, plateaus, then declines. Existing methods address this issue at the component level, targeting either the Questioner or the Solver, and overlook …