Self-Distillation Enables Continual Learning [pdf]

<a href="https://news.ycombinator.com/item?id=47757552">Comments</a>

<a href="https://news.ycombinator.com/item?id=49783133">Comments</a>

arXiv:2603.18620v1 Announce Type: cross Abstract: We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to

arXiv:2605.19447v1 Announce Type: new Abstract: Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a

arXiv:2605.11458v1 Announce Type: new Abstract: On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own