1
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
新方法SIRI让LLM智能体通过内在技能进行自我强化学习，提升训练效率与自主能力
arXiv:2606.02355v1 Announce Type: cross Abstract: Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rel…